Models

Qwen 2.5

7b

Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B-Instruct

700

1,828,561

Q
Warm

qwen25-7b-lc

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

328

1,759,738

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-7B

194

615,259

Q
Warm

qwen25-7b-lc

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

659

439,763

D
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Coder-7B-Instruct

493

403,405

Q
Warm

qwen25-7b-lc

Qwen/Qwen2.5-Math-7B

82

135,906

Q
Cold

qwen25-7b-lc

Qwen/Qwen2.5-Math-7B-Instruct

67

70,606

Q
Warm

qwen25-7b-lc

open-thoughts/OpenThinker-7B

129

33,370

O
Warm

qwen25-7b-lc

Kortix/FastApply-7B-v1.0

27

32,859

K
Cold

qwen25-7b-lc

Qwen/Qwen2.5-Coder-7B

109

30,500

Q
Cold

qwen25-7b-lc

unsloth/Qwen2.5-7B-Instruct

10

22,034

U
Cold

qwen25-7b-lc

unsloth/Qwen2.5-7B

4

21,524

U
Warm

qwen25-7b-lc

AI-MO/Kimina-Prover-Preview-Distill-7B

32

13,934

A
Cold

qwen25-7b-lc

unsloth/Qwen2.5-Coder-7B

3

12,237

U
Warm

qwen25-7b-lc

open-thoughts/OpenThinker3-7B

113

11,969

O
Cold

qwen25-7b-lc

pxyyy/Qwen2.5-7B-NuminaMath-CoT-smp20k-ep1-2e-5

0

8,433

P
Cold

qwen25-7b-lc

unsloth/Qwen2.5-Coder-7B-Instruct

5

7,686

U
Warm

qwen25-7b-lc

open-thoughts/OpenThinker2-7B

16

6,262

O
Warm

qwen25-7b-lc

nvidia/OpenCodeReasoning-Nemotron-7B

30

5,410

N
Warm

qwen25-7b-lc

AIDC-AI/Marco-o1

715

5,317

A