Models

Warm

llama31-8b-16k

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

4,705

7,090,908

M
Warm

qwen25-3b

Qwen/Qwen2.5-3B-Instruct

316

7,054,269

Q
Warm

llama31-8b-16k

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

4,708

6,958,075

M
Warm

qwen3-0b6

Qwen/Qwen3-0.6B

676

6,889,869

Q
Warm

llama32-1b

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

1,100

6,143,028

M
Warm

qwen3-32b

Qwen/Qwen3-32B

544

5,834,166

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

813

5,149,585

Q
Warm

qwen25-0b5

Gensyn/Qwen2.5-0.5B-Instruct

22

4,448,616

G
Warm

llama32-3b

context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16

7

3,195,017

C
Warm

qwen25-32b-lc

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

1,447

2,998,844

D
Warm

tinyllama-1b1

TinyLlama/TinyLlama-1.1B-Chat-v1.0

1,419

2,669,131

T
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

232

2,104,173

Q
Warm

qwen3-8b

Qwen/Qwen3-8B

653

2,086,701

Q
Warm

qwen3-4b

Qwen/Qwen3-4B-Instruct-2507

369

1,972,135

Q
Warm

llama3-8b-8k

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

6,340

1,921,267

M
Warm

llama32-1b

meta-llama/Llama-3.2-1B

2,101

1,911,894

M
Warm

llama32-3b

meta-llama/Llama-3.2-3B-Instruct

1,748

1,900,241

M
Warm

qwen25-0b5

Qwen/Qwen2.5-0.5B-Instruct

374

1,696,936

Q
Warm

qwen25-14b-lc

Qwen/Qwen2.5-14B-Instruct

276

1,617,526

Q
Warm

qwen3-4b

Qwen/Qwen3-4B

410

1,440,157

Q