Models

Llama 3.1

Warm

llama31-8b-16k

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

4,135

5,353,915

M
Warm

llama31-8b-16k

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

3,980

4,851,980

M
Warm

llama31-8b-16k

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

752

1,344,773

D
Warm

llama31-8b-16k

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

1,618

1,138,449

M
Loading

llama31-70b-16k

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

810

945,390

M
Cold

llama31-8b-16k

meta-llama/Llama-3.1-8B

1,661

943,079

M
Warm

llama31-8b-16k

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

200

344,134

M
Warm

llama31-8b-16k

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

185

178,387

N
Warm

llama31-8b-16k

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

75

155,273

U
Warm

llama31-70b-16k

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

365

83,050

M
Warm

llama31-8b-16k

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

17

75,261

S
Warm

llama31-8b-16k

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

322

65,353

N
Warm

llama31-8b-16k

unsloth/Llama-3.1-8B-Instruct

2

32,687

U
Warm

llama31-8b-16k

RLHFlow/Llama3.1-8B-PRM-Deepseek-Data

32

26,447

R
Cold

llama31-8b-16k

qqlabs/llama3_1_relevance_dev

0

24,144

Q
Cold

llama31-8b-16k

tokyotech-llm/Llama-3.1-Swallow-8B-v0.1

10

22,929

T
Warm

llama31-70b-16k

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

2,040

22,372

N
Warm

llama31-8b-16k

NousResearch/DeepHermes-3-Llama-3-8B-Preview

337

21,912

N
Warm

llama31-8b-16k

tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3

19

18,145

T
Warm

llama31-8b-16k

unsloth/DeepSeek-R1-Distill-Llama-8B

96

14,567

U