Models

Warm

llama31-8b

meta-llama/Llama-3.1-8B-Instruct

5,180

10,609,474

M
Warm

llama31-8b

meta-llama/Meta-Llama-3.1-8B-Instruct

5,180

10,609,474

M
Warm

qwen25-3b

Qwen/Qwen2.5-3B-Instruct

354

8,568,185

Q
Warm

qwen3-0b6

Qwen/Qwen3-0.6B

919

8,125,936

Q
Warm

qwen25-7b

Qwen/Qwen2.5-7B-Instruct

979

6,248,128

Q
Warm

qwen3-1b7

Qwen/Qwen3-1.7B

370

5,192,190

Q
Warm

qwen25-1b5

Qwen/Qwen2.5-1.5B-Instruct

575

5,066,649

Q
Warm

qwen25-0b5

Qwen/Qwen2.5-Coder-0.5B-Instruct

55

4,415,372

Q
Warm

qwen3-8b

Qwen/Qwen3-8B

832

4,356,796

Q
Warm

qwen3-4b

Qwen/Qwen3-4B-Instruct-2507

597

4,112,851

Q
Warm

qwen3-4b

Qwen/Qwen3-4B

507

3,739,725

Q
Warm

llama32-1b

meta-llama/Llama-3.2-1B-Instruct

1,221

3,241,150

M
Warm

qwen25-32b

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

1,480

2,735,518

D
Warm

qwen25-1b5

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

1,417

2,541,540

D
Warm

mistral-v02-7b

mistralai/Mistral-7B-Instruct-v0.2

3,043

2,490,734

M
Warm

gemma3t-1b

google/gemma-3-1b-it

775

2,419,879

G
Warm

qwen3-32b

Qwen/Qwen3-32B

607

2,277,619

Q
Warm

qwen25-0b5

Qwen/Qwen2.5-0.5B-Instruct

422

2,206,140

Q
Warm

llama3-8b

meta-llama/Meta-Llama-3-8B

6,410

2,196,302

M
Warm

qwen25-14b

Qwen/Qwen2.5-14B-Instruct

296

2,093,022

Q