5 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 · T4 · 16 GB

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

Qwen3-4B-AWQ
Qwen · 1 tested configuration
- AWQ · 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	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

unsloth · 2 tested configurations

nf4 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 90.1vectors/sec
Best measured · Batch 16: 809vectors/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	90.07	11 ms	—	0.75	56.2	2	2f9465c4 ↗
B4	302.9	13 ms	—	0.75	61.5	2	2f9465c4 ↗
B16	809.43	20 ms	—	0.75	64	2	2f9465c4 ↗

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: 1,002vectors/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	108.76	9 ms	—	0.89	50.3	2	cfe051ff ↗
B4	365.82	11 ms	—	0.89	58.1	2	cfe051ff ↗
B16	1,002.27	16 ms	—	0.89	63.9	2	cfe051ff ↗

embeddinggemma-2

google · 2 tested configurations

nf4 · 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 ↗

bge-small-zh-v1.5

BAAI · 1 tested configuration

nf4 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

Throughput · Batch 1: 1,170vectors/sec
Best measured · Batch 16: 5,188vectors/sec
Observed GPU occupancy: 0.3GiB
P95 latency: 1 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	1,169.81	1 ms	—	0.29	39	1	0fb03772 ↗
B4	2,301.06	2 ms	—	0.29	32.5	1	0fb03772 ↗
B16	5,188.01	3 ms	—	0.29	32.5	1	0fb03772 ↗

granite-embedding-97m-multilingual-r2

ibm-granite · 1 tested configuration

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

Throughput · Batch 1: 464vectors/sec
Best measured · Batch 16: 4,084vectors/sec
Observed GPU occupancy: 0.5GiB
P95 latency: 2 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	464.26	2 ms	—	0.47	45.4	1	37c260e4 ↗
B4	1,713.26	2 ms	—	0.47	49.4	1	37c260e4 ↗
B16	4,083.56	4 ms	—	0.47	38.3	1	37c260e4 ↗

Sortable tables by exact test condition · 20 rows

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	90.07	11 ms	—	0.75	56.2	2	2f9465c4 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	108.76	9 ms	—	0.89	50.3	2	cfe051ff ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	90.02	11 ms	—	0.75	54.6	2	43c67a74 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	108.65	9 ms	—	0.89	49.3	2	2846de88 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
bge-small-zh-v1.5	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	1,169.81	1 ms	—	0.29	39	1	0fb03772 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 1 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
granite-embedding-97m-multilingual-r2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	464.26	2 ms	—	0.47	45.4	1	37c260e4 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	302.9	13 ms	—	0.75	61.5	2	2f9465c4 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	365.82	11 ms	—	0.89	58.1	2	cfe051ff ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	303.35	13 ms	—	0.75	60.1	2	43c67a74 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	365.65	11 ms	—	0.89	57.9	2	2846de88 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
bge-small-zh-v1.5	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	2,301.06	2 ms	—	0.29	32.5	1	0fb03772 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 4 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
granite-embedding-97m-multilingual-r2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	1,713.26	2 ms	—	0.47	49.4	1	37c260e4 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	809.43	20 ms	—	0.75	64	2	2f9465c4 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	1,002.27	16 ms	—	0.89	63.9	2	cfe051ff ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	814.64	20 ms	—	0.75	64.1	2	43c67a74 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
embeddinggemma-2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	1,004.11	16 ms	—	0.89	63.9	2	2846de88 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
bge-small-zh-v1.5	T4 · 16 GB	nf4	sentence-transformersPyTorch 2.12.1+cu126	5,188.01	3 ms	—	0.29	32.5	1	0fb03772 ↗

Embedding · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s · Batch 16 · vectors/sec · 1 rows
Model	Hardware	Format	Engine	Mean throughput (vectors/sec)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
granite-embedding-97m-multilingual-r2	T4 · 16 GB	fp16	sentence-transformersPyTorch 2.12.1+cu126	4,083.56	4 ms	—	0.47	38.3	1	37c260e4 ↗

Text generation · 8K → 2K tokens · No cache reuse · 1 request · tok/s · 1 rows
Model	Hardware	Format	Engine	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Qwen3-4B-AWQ	T4 · 16 GB	AWQ	vllmvLLM 0.29.0	15.39	133.36 s	28.5 s	12.74	67.9	1	fcfe2d64 ↗

Text generation · 8K → 2K tokens · No cache reuse · 4 concurrent requests · tok/s · 1 rows
Model	Hardware	Format	Engine	Mean throughput (tok/s)	P95	TTFT	Observed occupancy (GiB)	GPU power (W)	Reports combined	View report
Qwen3-4B-AWQ	T4 · 16 GB	AWQ	vllmvLLM 0.29.0	20.31	468.13 s	53.1 s	12.74	67.5	1	fcfe2d64 ↗

Models with reports but no qualified results · 12

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 · 12 rows
Model	Test task
Qwen2.5-0.5Bqwen2.5:0.5b	Text generation
qwen2.5-0.5b-instruct-q4_k_m.ggufQwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf	Text generation
qwen2.5-1.5b-instruct-q4_k_m.ggufQwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf	Text generation
Qwen2.5-3Bqwen2.5:3b	Text generation
qwen2.5-3b-instruct-q4_k_m.ggufQwen/Qwen2.5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf	Text generation
Qwen2.5-7Bqwen2.5:7b	Text generation
Qwen3-0.6B-GPTQ-Int8Qwen/Qwen3-0.6B-GPTQ-Int8	Text generation
Qwen3-8B-AWQQwen/Qwen3-8B-AWQ	Text generation
Qwen3-14B-AWQQwen/Qwen3-14B-AWQ	Text generation
WeMM-Embedding-2Btencent/WeMM-Embedding-2B	Embedding
WeMM-Embedding-4Btencent/WeMM-Embedding-4B	Embedding
WeMM-Embedding-9Btencent/WeMM-Embedding-9B	Embedding

Get your startup command

All tasks · T4 · 16 GB

Qwen3-4B-AWQ

embeddinggemma-2

embeddinggemma-2

bge-small-zh-v1.5

granite-embedding-97m-multilingual-r2