Models

Warm

llama31-8b-16k

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

4,455

14,477,916

M
Warm

llama31-8b-16k

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

4,455

14,477,916

M
Warm

qwen25-14b-lc

Qwen/Qwen2.5-14B-Instruct

261

12,329,213

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

754

9,157,519

Q
Warm

qwen3-8b

Qwen/Qwen3-8B

531

5,206,466

Q
Warm

qwen25-0b5

Gensyn/Qwen2.5-0.5B-Instruct

20

3,654,433

G
Warm

llama32-3b

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

0

3,087,861

C
Warm

qwen25-1b5

Qwen/Qwen2.5-1.5B-Instruct

488

2,838,561

Q
Warm

qwen3-8b

Qwen/Qwen3-8B-Base

48

2,274,748

Q
Warm

llama32-3b

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

1,652

1,789,500

M
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct-1M

346

1,720,802

Q
Warm

qwen25-7b-lc

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

690

1,572,109

D
Warm

qwen3-1b7

Qwen/Qwen3-1.7B

228

1,430,037

Q
Warm

gemma3-4b

google/gemma-3-4b-it

781

1,365,277

G
Warm

tinyllama-1b1

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

1,363

1,232,729

T
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

213

1,153,305

Q
Warm

llama3-8b-8k

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

4,131

1,104,454

M
Warm

qwen25-32b-lc

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

1,427

1,100,926

D
Warm

phi3-4b

microsoft/Phi-3-mini-128k-instruct

1,661

1,097,812

M
Warm

llama31-8b-16k

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

782

1,067,207

D