0 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.

All tasks · RTX 3090 · 24 GB

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

No qualified results yet · All tasks · RTX 3090 · 24 GB

9 original reports are kept as evidence but do not qualify for comparison; each report states why. This does not show that the model or GPU cannot run it.

Check model launch support View original reports Measured alternatives for this task Test your own GPU

Measured alternatives on other GPUs

Measured on different GPUs with the same or smaller listed capacity. These are references for choosing hardware, not performance or compatibility evidence for your selected GPU.

Qwen3-4B-AWQ
Qwen · 3 tested configurations · 2 GPUs
- L4 · 24 GBAWQ · 8K → 2K tokens · No cache reuse
  Output throughput · includes prefill · 1 request
  55.3tok/s
  Best measured · 4 concurrent requests
  109tok/s
  Observed GPU occupancy
  19.5GiB
  First token
  1.6 s
  Use this recipe · 4 concurrent requests ↗Evidence report and run availability ↗Same test on other GPUs
  Test details · 2 concurrency levels
  Total output tokens divided by the full request window, including prefill and queueing.
  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 · vLLM 0.29.0
  Protocol
  wbench-fixed-http-v3
  Dataset
  migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=isolated:repeats=3
  Workload
  8192in-2048out
  Concurrency Mean throughput (tok/s) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  C1 55.3 37.17 s 1.6 s 19.54 71.9 1 9301a9ba ↗
  C4 109.43 78.88 s 3.1 s 19.55 71.9 1 9301a9ba ↗
- 1 other test configurations on this GPU
  - AWQ · 8K → 2K tokens · Prefix cache reuse
    Output throughput · includes prefill · 1 request
    57.4tok/s
    Best measured · 4 concurrent requests
    175tok/s
    Observed GPU occupancy
    19.5GiB
    First token
    60 ms
    Use this recipe · 4 concurrent requests ↗Evidence report and run availability ↗Same test on other GPUs
    Test details · 2 concurrency levels
    Total output tokens divided by the full request window, including prefill and queueing.
    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 · vLLM 0.29.0
    Protocol
    wbench-fixed-http-v3
    Dataset
    migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=prefix-reuse:repeats=3
    Workload
    8192in-2048out
    Concurrency Mean throughput (tok/s) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
    C1 57.39 35.7 s 60 ms 19.55 71.8 1 7e2cbfda ↗
    C4 175.39 46.75 s 114 ms 19.55 71.9 1 7e2cbfda ↗
Show 1 more GPUs
- T4 · 16 GBAWQ · 8K → 2K tokens · No cache reuse
  Output throughput · includes prefill · 1 request
  15.4tok/s
  Best measured · 4 concurrent requests
  20.3tok/s
  Observed GPU occupancy
  12.7GiB
  First token
  28.5 s
  Use this recipe · 4 concurrent requests ↗Evidence report and run availability ↗Same test on other GPUs
  Test details · 2 concurrency levels
  Total output tokens divided by the full request window, including prefill and queueing.
  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 · vLLM 0.29.0
  Protocol
  wbench-fixed-http-v3
  Dataset
  migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=isolated:repeats=3
  Workload
  8192in-2048out
  Concurrency Mean throughput (tok/s) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report
  C1 15.39 133.36 s 28.5 s 12.74 67.9 1 fcfe2d64 ↗
  C4 20.31 468.13 s 53.1 s 12.74 67.5 1 fcfe2d64 ↗

Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
C1	55.3	37.17 s	1.6 s	19.54	71.9	1	9301a9ba ↗
C4	109.43	78.88 s	3.1 s	19.55	71.9	1	9301a9ba ↗

Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
C1	57.39	35.7 s	60 ms	19.55	71.8	1	7e2cbfda ↗
C4	175.39	46.75 s	114 ms	19.55	71.9	1	7e2cbfda ↗

Concurrency	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
C1	15.39	133.36 s	28.5 s	12.74	67.9	1	fcfe2d64 ↗
C4	20.31	468.13 s	53.1 s	12.74	67.5	1	fcfe2d64 ↗

embeddinggemma-2

google · 4 tested configurations · 2 GPUs

L4 · 24 GBnf4 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 175vectors/sec
Best measured · Batch 16: 1,639vectors/sec
Observed GPU occupancy: 0.9GiB
P95 latency: 6 ms

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

Test details · 3 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: sentence-transformers · PyTorch 2.12.1+cu126
Protocol: native-forward-v1
Dataset: embedding-mteb-tasks-v1
Workload: embedding

Batch size	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	174.88	6 ms	—	0.85	53.1	6	7ad6a821 ↗
B4	571.03	7 ms	—	0.85	57	6	7ad6a821 ↗
B16	1,639.08	10 ms	—	0.85	59.8	6	7ad6a821 ↗

1 other test configurations on this GPU

fp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 177vectors/sec
Best measured · Batch 16: 2,039vectors/sec
Observed GPU occupancy: 1GiB
P95 latency: 6 ms

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

Test details · 3 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: sentence-transformers · PyTorch 2.12.1+cu126
Protocol: native-forward-v1
Dataset: embedding-mteb-tasks-v1
Workload: embedding

Batch size	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	177.46	6 ms	—	0.99	49.8	6	e0700e04 ↗
B4	650.16	6 ms	—	0.99	56.9	6	e0700e04 ↗
B16	2,039.17	8 ms	—	0.99	58.4	6	e0700e04 ↗

Show 1 more GPUs

T4 · 16 GBnf4 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 90vectors/sec
Best measured · Batch 16: 815vectors/sec
Observed GPU occupancy: 0.7GiB
P95 latency: 11 ms

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

Test details · 3 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: sentence-transformers · PyTorch 2.12.1+cu126
Protocol: native-forward-v1
Dataset: embedding-mteb-tasks-v1
Workload: embedding

Batch size	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	90.02	11 ms	—	0.75	54.6	2	43c67a74 ↗
B4	303.35	13 ms	—	0.75	60.1	2	43c67a74 ↗
B16	814.64	20 ms	—	0.75	64.1	2	43c67a74 ↗

1 other test configurations on this GPU

fp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 109vectors/sec
Best measured · Batch 16: 1,004vectors/sec
Observed GPU occupancy: 0.9GiB
P95 latency: 9 ms

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

Test details · 3 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: sentence-transformers · PyTorch 2.12.1+cu126
Protocol: native-forward-v1
Dataset: embedding-mteb-tasks-v1
Workload: embedding

Batch size	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
B1	108.65	9 ms	—	0.89	49.3	2	2846de88 ↗
B4	365.65	11 ms	—	0.89	57.9	2	2846de88 ↗
B16	1,004.11	16 ms	—	0.89	63.9	2	2846de88 ↗

Models with reports but no qualified results · 9

Their original reports remain available on each model page. They did not qualify for comparison; each report states why.

Models with reports but no qualified results · 9 rows
Model	Test task
DeepSeek-R1-Qwen3-8Bdeepseek-ai/DeepSeek-R1-0528-Qwen3-8B	Text generation
Qwen2.5-3B-AWQ/home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen2___5-3B-Instruct-AWQ	Text generation
Qwen2.5-7B-AWQ/home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct-AWQ	Text generation
Qwen2.5-14B-AWQ/home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen2___5-14B-Instruct-AWQ	Text generation
Qwen3-0.6BQwen/Qwen3-0.6B	Text generation
Qwen3-1.7BQwen/Qwen3-1.7B	Text generation
Qwen3-4BQwen/Qwen3-4B	Text generation
Qwen3-8B-AWQQwen/Qwen3-8B-AWQ	Text generation
Qwen3-14B-AWQQwen/Qwen3-14B-AWQ	Text generation

Get your startup command

All tasks · RTX 3090 · 24 GB

Measured alternatives on other GPUs

Qwen3-4B-AWQ

embeddinggemma-2