Models

Qwen 2.5

1b5

Warm

qwen25-1b5

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

1,394

1,181,722

D
Warm

qwen25-1b5

Gensyn/Qwen2.5-1.5B-Instruct

13

37,522

G
Warm

qwen25-1b5

mixedbread-ai/mxbai-rerank-large-v2

115

19,038

M
Warm

qwen25-1b5

AITeamVN/Vi-Qwen2-1.5B-RAG

3

9,168

A
Warm

qwen25-1b5

unsloth/Qwen2.5-1.5B-Instruct

8

9,027

U
Warm

qwen25-1b5

jinaai/ReaderLM-v2

727

8,370

J
Warm

qwen25-1b5

nvidia/Nemotron-Research-Reasoning-Qwen-1.5B

229

7,101

N
Warm

qwen25-1b5

RedHatAI/Qwen2-1.5B-Instruct-FP8

0

6,898

R
Warm

qwen25-1b5

katanemo/Arch-Router-1.5B

223

4,723

K
Warm

qwen25-1b5

Kortix/FastApply-1.5B-v1.0

39

3,492

K
Warm

qwen25-1b5

nm-testing/Qwen2-1.5B-Instruct-FP8-K-V

0

1,743

N
Warm

qwen25-1b5

MTSAIR/Cotype-Nano

54

1,641

M
Warm

qwen25-1b5

open-thoughts/OpenThinker3-1.5B

12

1,499

O
Warm

qwen25-1b5

nvidia/OpenMath-Nemotron-1.5B

25

1,427

N
Warm

qwen25-1b5

nvidia/OpenReasoning-Nemotron-1.5B

48

1,034

N
Warm

qwen25-1b5

Qwen/Qwen2-Math-1.5B

14

947

Q
Warm

qwen25-1b5

unsloth/Qwen2.5-Math-1.5B

4

944

U
Warm

qwen25-1b5

DeepMount00/Qwen2-1.5B-Ita

24

783

D
Warm

qwen25-1b5

e-palmisano/Qwen2-1.5B-ITA-Instruct

1

770

E
Warm

qwen25-1b5

Qwen/Qwen2-Math-1.5B-Instruct

21

690

Q