Models

Llama 3.1

Warm

llama31-8b

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

5,498

6,505,143

M
Warm

llama31-8b

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

5,497

6,505,143

M
Warm

llama31-8b

meta-llama/Llama-3.1-8B

2,081

1,275,445

M
Warm

llama31-8b

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

2,081

1,275,445

M
Warm

llama31-70b

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

894

749,814

M
Warm

llama31-70b

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

894

749,814

M
Warm

llama31-8b

NousResearch/Hermes-3-Llama-3.1-8B

389

613,653

N
Warm

llama31-8b

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

845

602,248

D
Warm

llama31-8b

unsloth/Meta-Llama-3.1-8B-Instruct

94

260,964

U
Warm

llama31-8b

NousResearch/Meta-Llama-3.1-8B-Instruct

39

197,245

N
Warm

llama31-8b

unsloth/Llama-3.1-8B-Instruct

9

161,139

U
Warm

llama31-8b

nvidia/Llama-3.1-Nemotron-Nano-8B-v1

218

132,944

N
Warm

llama31-8b

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

272

129,317

M
Warm

llama31-8b

nvidia/Llama-3.1-8B-Instruct-FP8

32

85,016

N
Warm

llama31-70b

meta-llama/Llama-3.1-70B

408

69,841

M
Warm

llama31-70b

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

408

69,841

M
Warm

llama31-8b

fdtn-ai/Foundation-Sec-1.1-8B-Instruct

13

52,369

F
Warm

llama31-70b

tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3

14

35,307

T
Warm

llama31-8b

Salesforce/Llama-xLAM-2-8b-fc-r

58

32,149

S
Warm

llama31-8b

watt-ai/watt-tool-8B

117

30,841

W