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

656

3,076,239

Q
Warm

qwen25-7b-lc

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

316

2,597,079

Q
Warm

qwen25-32b-lc

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

1,350

2,412,688

D
Warm

deepseek-v3-lc

deepseek-ai/DeepSeek-R1

11,993

1,802,384

D
Warm

mistral-v02-7b-std-lc

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

2,729

1,314,251

M
Warm

llama31-70b-16k

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

805

1,197,622

M
Warm

qwen25-7b-lc

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

619

1,090,513

D
Warm

llama33-70b-16k

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

2,276

1,087,762

M
Loading

llama3-8b-8k

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

3,930

1,087,151

M
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

899

951,954

M
Warm

qwen25-14b-lc

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

502

934,186

D
Warm

qwen25-14b-lc

Qwen/Qwen2.5-14B-Instruct

229

871,066

Q
Warm

llama31-8b-16k

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

703

867,052

D
Warm

qwen25-32b-lc

Qwen/QwQ-32B

2,713

658,260

Q
Warm

mistral-v02-7b-std-lc

HuggingFaceH4/zephyr-7b-beta

1,692

615,879

H
Cold

llama3-8b-8k

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

6,148

553,797

M
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

176

535,237

Q