Models

Warm

llama31-8b-16k

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

3,784

6,047,201

M
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

661

3,131,031

Q
Warm

qwen25-7b-lc

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

319

2,430,206

Q
Warm

qwen25-32b-lc

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

1,354

2,224,933

D
Warm

deepseek-v3-lc

deepseek-ai/DeepSeek-R1

12,022

1,737,287

D
Warm

llama31-70b-16k

meta-llama/Meta-Llama-3.1-70B-Instruct

805

1,197,622

M
Loading

llama3-8b-8k

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

3,933

1,125,889

M
Warm

mistral-v02-7b-std-lc

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

2,735

1,079,879

M
Warm

llama33-70b-16k

meta-llama/Llama-3.3-70B-Instruct

2,282

1,065,834

M
Warm

qwen25-7b-lc

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

623

1,026,718

D
Warm

llama31-8b-16k

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

1,531

986,413

M
Warm

gemma3-27b

google/gemma-3-27b-it

1,099

964,080

G
Warm

mistral-24b-lc

mistralai/Mistral-Small-24B-Instruct-2501

901

908,019

M
Warm

qwen25-14b-lc

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

504

877,741

D
Warm

llama31-8b-16k

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

707

869,553

D
Warm

qwen25-14b-lc

Qwen/Qwen2.5-14B-Instruct

231

850,731

Q
Warm

qwen25-32b-lc

Qwen/QwQ-32B

2,731

644,822

Q
Warm

mistral-v02-7b-std-lc

HuggingFaceH4/zephyr-7b-beta

1,694

612,502

H
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

176

541,691

Q
Cold

llama3-8b-8k

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

6,151

538,126

M