Models

Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

793

7,794,184

Q
Warm

llama31-8b-16k

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

4,627

7,230,352

M
Warm

llama31-8b-16k

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

4,627

7,230,352

M
Warm

qwen25-32b-lc

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

1,444

2,864,129

D
Warm

llama31-8b-16k

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

799

2,822,372

D
Warm

qwen3-8b

Qwen/Qwen3-8B

605

2,144,926

Q
Warm

llama3-8b-8k

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

6,316

2,043,605

M
Warm

tinyllama-1b1

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

1,403

1,903,232

T
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

226

1,648,728

Q
Warm

llama31-8b-16k

meta-llama/Llama-3.1-8B

1,802

1,260,677

M
Warm

llama31-8b-16k

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

1,802

1,260,677

M
Warm

qwen3-14b

Qwen/Qwen3-14B

268

1,141,371

Q
Warm

qwen25-7b-lc

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

720

1,138,349

D
Warm

qwen25-14b-lc

Qwen/Qwen2.5-14B-Instruct

272

1,129,371

Q
Warm

qwen3-32b

Qwen/Qwen3-32B

535

1,116,355

Q
Warm

mistral-v02-7b-std-lc

HuggingFaceH4/zephyr-7b-beta

1,777

1,096,697

H
Warm

llama3-8b-8k

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

4,182

1,019,197

M
Warm

deepseek-v3-lc

deepseek-ai/DeepSeek-R1-0528

2,365

1,004,675

D
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Coder-7B-Instruct

540

982,775

Q
Warm

gemma3-27b

google/gemma-3-27b-it

1,610

869,897

G