7 models with qualified results

Models

Measured configurations by model. Open a model to compare GPUs on one exact test.

Get your startup command

Choose your operating system and enter a model repository. Launch support is checked separately from performance results.

Decision · All measured GPUs

Speeds compare only within one exact test. Recipe availability is checked on each report against the published recipe executor.

StartLux-Decision-v1-0.8B
startlux-models · 2 tested configurations · 1 GPU
- RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 1
  50.3decisions/sec
  Observed GPU occupancy
  3.2GiB
  P95 latency
  20 ms
  Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  startlux-native · PyTorch 2.11.0+cu130
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 50.25 20 ms — 3.17 161.3 1 df141700 ↗
- 1 other test configurations on this GPU
  - bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
    Throughput · Batch 1
    50.3decisions/sec
    Observed GPU occupancy
    2.3GiB
    P95 latency
    20 ms
    Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
    Test details
    Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
    Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
    Engine
    startlux-native · PyTorch 2.11.0+cu130
    Protocol
    native-forward-v1
    Dataset
    typed-invoices-v1
    Workload
    decision
    Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
    B1 50.28 20 ms — 2.29 165 1 8c1985ea ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	50.25	20 ms	—	3.17	161.3	1	df141700 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	50.28	20 ms	—	2.29	165	1	8c1985ea ↗

Intern-Decision-0.8B

internlm · 4 tested configurations · 1 GPU

RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
Throughput · Batch 1
50.8decisions/sec
Best measured · Batch 17
347decisions/sec
Observed GPU occupancy
2.4GiB
P95 latency
20 ms
Use this recipe · Batch 17 ↗Evidence report and run availability ↗Same test on other GPUs
Test details · 2 batch sizes
Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
Engine
intern-decision-native · PyTorch 2.11.0+cu130
Protocol
native-forward-v1
Dataset
typed-invoices-v1
Workload
decision
Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
B1 50.83 20 ms — 2.36 169 2 18b06f63 ↗
B17 346.72 50 ms — 3.07 378 1 6ccb367c ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	50.83	20 ms	—	2.36	169	2	18b06f63 ↗
B17	346.72	50 ms	—	3.07	378	1	6ccb367c ↗

3 other test configurations on this GPU

bf16 · Text → Structured data · typed-invoices-v1 · Test duration 399 s

Throughput · Batch 1: 52decisions/sec
Best measured · Batch 16: 334decisions/sec
Observed GPU occupancy: 2.4GiB
P95 latency: 20 ms

Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs

Test details · 21 batch sizes

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

Engine: intern-decision-native · PyTorch 2.11.0
Protocol: native-forward-v1
Dataset: typed-invoices-v1
Workload: decision

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	52.04	20 ms	—	2.36	162.6	1	156910e7 ↗
B2	96.21	21 ms	—	2.38	213.4	1	156910e7 ↗
B4	177.08	23 ms	—	2.43	243.4	1	156910e7 ↗
B8	299.06	27 ms	—	2.57	341.2	1	156910e7 ↗
B12	306.24	40 ms	—	36.98	349.6	1	156910e7 ↗
B14	322.36	43 ms	—	36.98	365.9	1	156910e7 ↗
B15	328.14	46 ms	—	36.98	369.8	1	156910e7 ↗
B16	333.92	48 ms	—	3.19	368.4	1	156910e7 ↗
B17	331.9	52 ms	—	36.98	379.5	1	156910e7 ↗
B18	310.84	58 ms	—	36.98	365.4	1	156910e7 ↗
B20	316.13	64 ms	—	36.98	375.1	1	156910e7 ↗
B24	312.87	77 ms	—	36.98	377.5	1	156910e7 ↗
B28	309.61	91 ms	—	36.98	379.4	1	156910e7 ↗
B32	319.44	101 ms	—	3.44	376.3	1	156910e7 ↗
B40	307.24	131 ms	—	36.98	379.6	1	156910e7 ↗
B48	306.75	159 ms	—	36.98	380.4	1	156910e7 ↗
B64	304.06	213 ms	—	4.2	383.7	1	156910e7 ↗
B128	285.17	453 ms	—	6.23	387.8	1	156910e7 ↗
B256	284.61	904 ms	—	10.63	390.3	1	156910e7 ↗
B512	282.22	2.04 s	—	19.42	390.1	1	156910e7 ↗
B1024	286.53	3.58 s	—	36.98	396.2	1	156910e7 ↗

bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
Throughput · Batch 1
51.5decisions/sec
Observed GPU occupancy
2.6GiB
P95 latency
20 ms
Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
Test details
Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
Engine
intern-decision-native · PyTorch 2.11.0
Protocol
native-forward-v1
Dataset
typed-invoices-v1
Workload
decision
Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
B1 51.51 20 ms — 2.6 164.2 1 7f2e07c0 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	51.51	20 ms	—	2.6	164.2	1	7f2e07c0 ↗

bf16 · Text → Structured data · typed-invoices-v1 · Test duration 396 s

Throughput · Batch 1: 52.8decisions/sec
Best measured · Batch 17: 350decisions/sec
Observed GPU occupancy: 2.4GiB
P95 latency: 19 ms

Use this recipe · Batch 17 ↗Evidence report and run availability ↗Same test on other GPUs

Test details · 21 batch sizes

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

Engine: intern-decision-native · PyTorch 2.11.0
Protocol: native-forward-v1
Dataset: typed-invoices-v1
Workload: decision

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	52.8	19 ms	—	2.36	172.8	1	5eef633e ↗
B2	95.72	21 ms	—	2.38	186.5	1	5eef633e ↗
B4	177.64	23 ms	—	2.43	242	1	5eef633e ↗
B8	306.42	26 ms	—	2.57	344.2	1	5eef633e ↗
B12	322.68	37 ms	—	37.46	371.9	1	5eef633e ↗
B13	336	39 ms	—	37.46	380.8	1	5eef633e ↗
B14	344.61	41 ms	—	37.46	392.6	1	5eef633e ↗
B15	345.75	44 ms	—	37.46	389.5	1	5eef633e ↗
B16	345.28	47 ms	—	2.85	383.9	1	5eef633e ↗
B17	349.83	49 ms	—	37.46	397.8	1	5eef633e ↗
B18	327.34	55 ms	—	37.46	383.4	1	5eef633e ↗
B20	333.21	60 ms	—	37.46	402.6	1	5eef633e ↗
B24	331.98	73 ms	—	37.46	401.2	1	5eef633e ↗
B28	327.01	86 ms	—	37.46	399.2	1	5eef633e ↗
B32	331.67	97 ms	—	3.41	397.7	1	5eef633e ↗
B48	326.46	148 ms	—	37.46	405.9	1	5eef633e ↗
B64	318.22	202 ms	—	4.51	403.2	1	5eef633e ↗
B128	298.77	430 ms	—	6.71	405.8	1	5eef633e ↗
B256	298.58	859 ms	—	11.11	407.3	1	5eef633e ↗
B512	299.67	1.71 s	—	19.9	411.2	1	5eef633e ↗
B1024	297.46	3.64 s	—	37.46	410.6	1	5eef633e ↗

clef-flash

Cloudflare · 6 tested configurations · 2 GPUs

RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 33 s

Throughput · Batch 1: 31.8decisions/sec
Best measured · Batch 4: 39.3decisions/sec
Observed GPU occupancy: 18.9GiB
P95 latency: 32 ms

Use this recipe · Batch 4 ↗Evidence report and run availability ↗Same test on other GPUs

Test details · 4 batch sizes

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

Engine: clef-native · PyTorch 2.11.0
Protocol: native-forward-v1
Dataset: typed-invoices-v1
Workload: decision

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	31.83	32 ms	—	18.95	388.5	1	10c64aff ↗
B4	39.27	93 ms	—	18.95	449.5	1	10c64aff ↗
B16	5.41	8.21 s	—	19.28	233.4	1	10c64aff ↗
B64	15.43	9.66 s	—	21.89	324.3	1	10c64aff ↗

1 other test configurations on this GPU
- bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 16
  47.7decisions/sec
  Observed GPU occupancy
  19.5GiB
  P95 latency
  338 ms
  Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  clef-native · PyTorch 2.11.0+cu130
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B16 47.71 338 ms — 19.55 499.5 2 82d98b36 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B16	47.71	338 ms	—	19.55	499.5	2	82d98b36 ↗

vGPU-32GB · 32 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 1 s
Throughput · Batch 1
10.3decisions/sec
Best measured · Batch 4
10.9decisions/sec
Observed GPU occupancy
18.2GiB
P95 latency
104 ms
Use this recipe · Batch 4 ↗Evidence report and run availability ↗Same test on other GPUs
Test details · 2 batch sizes
Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
Engine
clef-native
Protocol
native-forward-v1
Dataset
typed-invoices-v1
Workload
decision
Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
B1 10.26 104 ms — 18.17 67.9 1 1d1661ad ↗
B4 10.89 389 ms — 18.49 156 1 1d1661ad ↗
3 other test configurations on this GPU
- bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 1
  10.6decisions/sec
  Best measured · Batch 4
  11decisions/sec
  Observed GPU occupancy
  18.2GiB
  P95 latency
  99 ms
  Use this recipe · Batch 4 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details · 2 batch sizes
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  clef-native · PyTorch 2.13.0+cu130
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 10.56 99 ms — 18.17 206.1 2 63f44036 ↗
  B4 11.04 402 ms — 18.55 244.4 2 63f44036 ↗
- bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 1
  10.6decisions/sec
  Best measured · Batch 4
  11.1decisions/sec
  Observed GPU occupancy
  18.2GiB
  P95 latency
  103 ms
  Use this recipe · Batch 4 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details · 2 batch sizes
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  clef-native
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 10.56 103 ms — 18.17 196.8 1 4eb73a4d ↗
  B4 11.1 390 ms — 18.56 235.9 1 4eb73a4d ↗
- bf16 · 1K → 1K tokens
  Throughput · Batch 1
  10.2decisions/sec
  Best measured · Batch 4
  10.9decisions/sec
  Observed GPU occupancy
  18.2GiB
  P95 latency
  104 ms
  Use this recipe · Batch 4 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details · 2 batch sizes
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  vLLM
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 10.19 104 ms — 18.17 69.8 1 caef7154 ↗
  B4 10.88 388 ms — 18.49 152.8 1 caef7154 ↗

StartLux-Decision-v1.1-0.8B-Instant
startlux-models · 2 tested configurations · 1 GPU
- RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 1
  18.7decisions/sec
  Observed GPU occupancy
  2.7GiB
  P95 latency
  54 ms
  Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  startlux-transformers · PyTorch 2.11.0+cu130
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 18.69 54 ms — 2.73 134.5 2 a4a69815 ↗
- 1 other test configurations on this GPU
  - bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
    Throughput · Batch 1
    18.8decisions/sec
    Observed GPU occupancy
    2.5GiB
    P95 latency
    54 ms
    Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
    Test details
    Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
    Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
    Engine
    startlux-transformers · PyTorch 2.11.0
    Protocol
    native-forward-v1
    Dataset
    typed-invoices-v1
    Workload
    decision
    Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
    B1 18.83 54 ms — 2.54 125.5 1 c342a9ca ↗
Intern-Decision-2B
internlm · 1 tested configuration · 1 GPU
- RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
  Throughput · Batch 1
  50.3decisions/sec
  Observed GPU occupancy
  4.9GiB
  P95 latency
  21 ms
  Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
  Test details
  Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
  Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.
  Engine
  intern-decision-native · PyTorch 2.11.0
  Protocol
  native-forward-v1
  Dataset
  typed-invoices-v1
  Workload
  decision
  Batch size Mean throughput (decisions/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  B1 50.29 21 ms — 4.9 216.2 1 e4bcd6a3 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	10.26	104 ms	—	18.17	67.9	1	1d1661ad ↗
B4	10.89	389 ms	—	18.49	156	1	1d1661ad ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	10.56	99 ms	—	18.17	206.1	2	63f44036 ↗
B4	11.04	402 ms	—	18.55	244.4	2	63f44036 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	10.56	103 ms	—	18.17	196.8	1	4eb73a4d ↗
B4	11.1	390 ms	—	18.56	235.9	1	4eb73a4d ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	10.19	104 ms	—	18.17	69.8	1	caef7154 ↗
B4	10.88	388 ms	—	18.49	152.8	1	caef7154 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	18.69	54 ms	—	2.73	134.5	2	a4a69815 ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	18.83	54 ms	—	2.54	125.5	1	c342a9ca ↗

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	50.29	21 ms	—	4.9	216.2	1	e4bcd6a3 ↗

clef-omni

Cloudflare · 1 tested configuration · 1 GPU

RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 44 s

Throughput · Batch 1: 7.5decisions/sec
Best measured · Batch 64: 7.5decisions/sec
Observed GPU occupancy: 60.9GiB
P95 latency: 134 ms

Use this recipe · Batch 64 ↗Evidence report and run availability ↗Same test on other GPUs

Test details · 4 batch sizes

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

Engine: clef-native · PyTorch 2.11.0
Protocol: native-forward-v1
Dataset: typed-invoices-v1
Workload: decision

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	7.45	134 ms	—	60.88	232.8	1	16597f91 ↗
B4	7.47	537 ms	—	60.89	249.7	1	16597f91 ↗
B16	7.48	2.14 s	—	60.89	252.8	1	16597f91 ↗
B64	7.49	8.56 s	—	60.89	257.2	1	16597f91 ↗

clef

Cloudflare · 1 tested configuration · 1 GPU

RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 46 s

Throughput · Batch 1: 12.3decisions/sec
Observed GPU occupancy: 52.4GiB
P95 latency: 82 ms

Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs

Test details · 4 batch sizes

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

Engine: clef-native · PyTorch 2.11.0
Protocol: native-forward-v1
Dataset: typed-invoices-v1
Workload: decision

Batch size	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	12.32	82 ms	—	52.4	469.1	1	243b7f64 ↗
B4	1.4	8.09 s	—	52.4	225.7	1	243b7f64 ↗
B16	4.33	9.1 s	—	52.98	308.5	1	243b7f64 ↗
B64	9.39	12.46 s	—	57.95	435.9	1	243b7f64 ↗

Sortable tables by exact test condition · 71 rows

Decision · 1K → 1K tokens · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	vLLM	10.19	104 ms	—	18.17	69.8	1	caef7154 ↗

Decision · 1K → 1K tokens · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	vLLM	10.88	388 ms	—	18.49	152.8	1	caef7154 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 1 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-native	10.26	104 ms	—	18.17	67.9	1	1d1661ad ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 1 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-native	10.89	389 ms	—	18.49	156	1	1d1661ad ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
StartLux-Decision-v1-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	startlux-nativePyTorch 2.11.0+cu130	50.25	20 ms	—	3.17	161.3	1	df141700 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
StartLux-Decision-v1-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	startlux-nativePyTorch 2.11.0+cu130	50.28	20 ms	—	2.29	165	1	8c1985ea ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0+cu130	50.83	20 ms	—	2.36	169	2	18b06f63 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	51.51	20 ms	—	2.6	164.2	1	7f2e07c0 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-nativePyTorch 2.13.0+cu130	10.56	99 ms	—	18.17	206.1	2	63f44036 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-native	10.56	103 ms	—	18.17	196.8	1	4eb73a4d ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
StartLux-Decision-v1.1-0.8B-Instant	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	startlux-transformersPyTorch 2.11.0+cu130	18.69	54 ms	—	2.73	134.5	2	a4a69815 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
StartLux-Decision-v1.1-0.8B-Instant	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	startlux-transformersPyTorch 2.11.0	18.83	54 ms	—	2.54	125.5	1	c342a9ca ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-2B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	50.29	21 ms	—	4.9	216.2	1	e4bcd6a3 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-nativePyTorch 2.13.0+cu130	11.04	402 ms	—	18.55	244.4	2	63f44036 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	vGPU-32GB · 32 GB	bf16	clef-native	11.1	390 ms	—	18.56	235.9	1	4eb73a4d ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0+cu130	47.71	338 ms	—	19.55	499.5	2	82d98b36 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 6 s · Batch 17 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0+cu130	346.72	50 ms	—	3.07	378	1	6ccb367c ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 33 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	31.83	32 ms	—	18.95	388.5	1	10c64aff ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 33 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	39.27	93 ms	—	18.95	449.5	1	10c64aff ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 33 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	5.41	8.21 s	—	19.28	233.4	1	10c64aff ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 33 s · Batch 64 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-flash	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	15.43	9.66 s	—	21.89	324.3	1	10c64aff ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 44 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-omni	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	7.45	134 ms	—	60.88	232.8	1	16597f91 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 44 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-omni	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	7.47	537 ms	—	60.89	249.7	1	16597f91 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 44 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-omni	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	7.48	2.14 s	—	60.89	252.8	1	16597f91 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 44 s · Batch 64 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef-omni	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	7.49	8.56 s	—	60.89	257.2	1	16597f91 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 46 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	12.32	82 ms	—	52.4	469.1	1	243b7f64 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 46 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	1.4	8.09 s	—	52.4	225.7	1	243b7f64 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 46 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	4.33	9.1 s	—	52.98	308.5	1	243b7f64 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 46 s · Batch 64 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
clef	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	clef-nativePyTorch 2.11.0	9.39	12.46 s	—	57.95	435.9	1	243b7f64 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	52.8	19 ms	—	2.36	172.8	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 2 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	95.72	21 ms	—	2.38	186.5	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	177.64	23 ms	—	2.43	242	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 8 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	306.42	26 ms	—	2.57	344.2	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 12 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	322.68	37 ms	—	37.46	371.9	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 13 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	336	39 ms	—	37.46	380.8	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 14 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	344.61	41 ms	—	37.46	392.6	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 15 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	345.75	44 ms	—	37.46	389.5	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	345.28	47 ms	—	2.85	383.9	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 17 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	349.83	49 ms	—	37.46	397.8	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 18 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	327.34	55 ms	—	37.46	383.4	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 20 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	333.21	60 ms	—	37.46	402.6	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 24 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	331.98	73 ms	—	37.46	401.2	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 28 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	327.01	86 ms	—	37.46	399.2	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 32 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	331.67	97 ms	—	3.41	397.7	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 48 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	326.46	148 ms	—	37.46	405.9	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 64 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	318.22	202 ms	—	4.51	403.2	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 128 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	298.77	430 ms	—	6.71	405.8	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 256 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	298.58	859 ms	—	11.11	407.3	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 512 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	299.67	1.71 s	—	19.9	411.2	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 396 s · Batch 1024 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	297.46	3.64 s	—	37.46	410.6	1	5eef633e ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 1 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	52.04	20 ms	—	2.36	162.6	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 2 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	96.21	21 ms	—	2.38	213.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 4 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	177.08	23 ms	—	2.43	243.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 8 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	299.06	27 ms	—	2.57	341.2	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 12 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	306.24	40 ms	—	36.98	349.6	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 14 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	322.36	43 ms	—	36.98	365.9	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 15 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	328.14	46 ms	—	36.98	369.8	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 16 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	333.92	48 ms	—	3.19	368.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 17 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	331.9	52 ms	—	36.98	379.5	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 18 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	310.84	58 ms	—	36.98	365.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 20 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	316.13	64 ms	—	36.98	375.1	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 24 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	312.87	77 ms	—	36.98	377.5	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 28 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	309.61	91 ms	—	36.98	379.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 32 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	319.44	101 ms	—	3.44	376.3	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 40 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	307.24	131 ms	—	36.98	379.6	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 48 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	306.75	159 ms	—	36.98	380.4	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 64 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	304.06	213 ms	—	4.2	383.7	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 128 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	285.17	453 ms	—	6.23	387.8	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 256 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	284.61	904 ms	—	10.63	390.3	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 512 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	282.22	2.04 s	—	19.42	390.1	1	156910e7 ↗

Decision · Text → Structured data · typed-invoices-v1 · Test duration 399 s · Batch 1024 · decisions/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (decisions/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Intern-Decision-0.8B	RTX PRO 6000 Blackwell Server Edition · 96 GB	bf16	intern-decision-nativePyTorch 2.11.0	286.53	3.58 s	—	36.98	396.2	1	156910e7 ↗

Get your startup command

Decision · All measured GPUs

StartLux-Decision-v1-0.8B

Intern-Decision-0.8B

clef-flash

StartLux-Decision-v1.1-0.8B-Instant

Intern-Decision-2B

clef-omni

clef