Models

Llama 3.1

8b

Warm

llama31-8b

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

4,973

5,155,971

M
Warm

llama31-8b

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

4,973

5,155,971

M
Warm

llama31-8b

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

824

1,061,563

D
Warm

llama31-8b

meta-llama/Llama-3.1-8B

1,925

600,824

M
Warm

llama31-8b

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

1,925

600,824

M
Warm

llama31-8b

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

368

256,471

N
Warm

llama31-8b

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

91

249,196

U
Warm

llama31-8b

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

37

194,797

N
Warm

llama31-8b

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

244

106,810

M
Warm

llama31-8b

context-labs/Meta-Llama-3.1-8B-Instruct-FP16

1

74,899

C
Warm

llama31-8b

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

30

35,214

N
Warm

llama31-8b

unsloth/Llama-3.1-8B-Instruct

7

32,336

U
Warm

llama31-8b

unsloth/Meta-Llama-3.1-8B

42

20,826

U
Warm

llama31-8b

KISTI-KONI/KONI-Llama3.1-8B-Instruct-20241024

1

15,383

K
Warm

llama31-8b

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

55

15,055

F
Warm

llama31-8b

tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5

14

13,693

T
Warm

llama31-8b

aisingapore/Llama-SEA-LION-v3.5-8B-R

11

12,714

A
Warm

llama31-8b

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

211

11,810

N
Warm

llama31-8b

qqlabs/llama3_1_relevance_dev

1

10,041

Q
Warm

llama31-8b

PatronusAI/Llama-3-Patronus-Lynx-8B-Instruct-v1.1

10

8,041

P