Top Qwen Fine-Tunes

Best fine-tunes built on Alibaba's Qwen family — Qwen2, Qwen2.5, and Qwen3.

Last updated April 3, 2026 · Updated daily

Qwen3.5-35B-A3B-GGUF by unsloth holds the #1 position with 1.7M downloads, ahead of Qwen3.5-9B-GGUF at 1.3M.

The top 10 is dominated by unsloth, lmstudio-community, RedHatAI. This is the first snapshot — future updates will track position changes and emerging trends.

The gap between #1 and #100 is 1.7M vs 160.2K downloads, showing significant concentration at the top.

🥇new

Qwen3.5-35B-A3B-GGUF

Silver53

unsloth · VLM · from Qwen/Qwen3.5-35B-A3B

1.7M

downloads

🥈new

Qwen3.5-9B-GGUF

Silver51

unsloth · VLM · from Qwen/Qwen3.5-9B

1.3M

downloads

🥉new

Qwen3.5-9B-GGUF

Bronze43

lmstudio-community · Other · from Qwen/Qwen3.5-9B

1.3M

downloads

4new

Qwen2.5-1.5B-quantized.w8a8

Bronze37

RedHatAI · Chat & Assistants · from Qwen/Qwen2.5-1.5B

894.7K

downloads

5new

Qwen3.5-27B-GGUF

Silver50

unsloth · VLM · from Qwen/Qwen3.5-27B

836.3K

downloads

6new

OneThinker-SFT-Qwen3-8B

Bronze37

OneThink · Other · from Qwen/Qwen3-VL-8B-Instruct

794.5K

downloads

7new

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Silver50

Jackrong · VLM · from Qwen/Qwen3.5-27B

771.6K

downloads

8new

Qwen3.5-35B-A3B-AWQ-4bit

Bronze42

cyankiwi · VLM · from Qwen/Qwen3.5-35B-A3B

653.5K

downloads

9new

Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive

Silver52

HauhauCS · VLM · from Qwen/Qwen3.5-35B-A3B

652.3K

downloads

10new

Qwen3-VL-30B-A3B-Instruct-AWQ

Bronze43

QuantTrio · Chat & Assistants · from Qwen/Qwen3-VL-30B-A3B-Instruct

649.0K

downloads

11new

Qwen3-14B-Instruct

Bronze40

OpenPipe · Chat & Assistants · from Qwen/Qwen3-14B-Base

648.2K

downloads

12new

Qwen3.5-4B-GGUF

Bronze47

unsloth · VLM · from Qwen/Qwen3.5-4B

580.3K

downloads

13new

Qwen3-VL-4B-Instruct-AWQ-4bit

Bronze38

cyankiwi · VLM · from Qwen/Qwen3-VL-4B-Instruct

561.1K

downloads

14new

Molmo2-8B

Bronze46

allenai · VLM · from Qwen/Qwen3-8B

529.7K

downloads

15new

Qwen3-Coder-Next-NVFP4

Bronze42

GadflyII · Code Generation · from Qwen/Qwen3-Coder-Next

527.0K

downloads

16new

Qwen3.5-4B-FP8

Bronze34

lovedheart · VLM · from Qwen/Qwen3.5-4B

516.2K

downloads

17new

InternVL2-1B

Bronze44

OpenGVLab · VLM · from merge:Qwen/Qwen2-0.5B-Instruct

502.8K

downloads

18new

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Silver53

Jackrong · VLM · from Qwen/Qwen3.5-27B

487.4K

downloads

19new

Qwen3-Coder-Next-8bit

Bronze34

NexVeridian · Code Generation · from Qwen/Qwen3-Coder-Next

457.7K

downloads

20new

Qwen3.5-122B-A10B-GGUF

Bronze46

unsloth · VLM · from Qwen/Qwen3.5-122B-A10B

450.6K

downloads

21new

VibeVoice-Realtime-0.5B

Silver51

microsoft · TTS · from Qwen/Qwen2.5-0.5B

447.0K

downloads

22new

Qwen3.5-35B-A3B-GGUF

Bronze40

lmstudio-community · Other · from Qwen/Qwen3.5-35B-A3B

417.2K

downloads

23new

Qwen2.5-72B-Instruct-abliterated

Bronze42

huihui-ai · Chat & Assistants (Uncensored) · from Qwen/Qwen2.5-72B-Instruct

414.2K

downloads

24new

olmOCR-2-7B-1025

Bronze45

allenai · VLM · from Qwen/Qwen2.5-VL-7B-Instruct

401.1K

downloads

25new

Qwen3-Coder-30B-A3B-Instruct-gptq-8bit

Bronze36

btbtyler09 · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

400.7K

downloads

26new

OTel-LLM-1.7B-IT

Bronze32

farbodtavakkoli · LLM - General · from Qwen/Qwen3-1.7B

396.4K

downloads

27new

Qwen3.5-27B-AWQ

Bronze41

QuantTrio · VLM · from Qwen/Qwen3.5-27B

393.0K

downloads

28new

OTel-LLM-0.6B-IT

Bronze32

farbodtavakkoli · LLM - General · from Qwen/Qwen3-0.6B

377.2K

downloads

29new

Qwen3-14B-NVFP4

Bronze36

nvidia · LLM - General · from Qwen/Qwen3-14B

366.8K

downloads

30new

OTel-Reranker-0.6B

Bronze32

farbodtavakkoli · Other · from Qwen/Qwen3-0.6B

363.9K

downloads

31new

Qwen-Image-Lightning

Bronze49

lightx2v · Image Generation · from adapter:Qwen/Qwen-Image

360.1K

downloads

32new

turn-detector

Bronze43

livekit · Other · from Qwen/Qwen2.5-0.5B-Instruct

349.8K

downloads

33new

OTel-Embedding-0.6B

Bronze32

farbodtavakkoli · Embeddings · from Qwen/Qwen3-Embedding-0.6B

338.5K

downloads

34new

OTel-Embedding-4B

Bronze32

farbodtavakkoli · Embeddings · from Qwen/Qwen3-Embedding-4B

334.7K

downloads

35new

Nanonets-OCR2-3B

Bronze48

nanonets · VLM · from Qwen/Qwen2.5-VL-3B-Instruct

331.2K

downloads

36new

Qwen3.5-122B-A10B-NVFP4

Bronze42

Sehyo · VLM · from Qwen/Qwen3.5-122B-A10B

325.7K

downloads

37new

Qwen3-Coder-Next-MLX-4bit

Bronze39

lmstudio-community · Other · from Qwen/Qwen3-Coder-Next

311.7K

downloads

38new

Qwen3-Coder-Next-MLX-8bit

Bronze37

lmstudio-community · Other · from Qwen/Qwen3-Coder-Next

311.5K

downloads

39new

Qwen3.5-0.8B-GGUF

Bronze44

unsloth · VLM · from Qwen/Qwen3.5-0.8B

310.4K

downloads

40new

Qwen2.5-Coder-7B-Instruct-GGUF

Bronze41

bartowski · Code Generation · from Qwen/Qwen2.5-Coder-7B-Instruct

308.3K

downloads

41new

Qwen3.5-9B-AWQ

Bronze37

QuantTrio · VLM · from Qwen/Qwen3.5-9B

297.1K

downloads

42new

Qwen3-Coder-Next-GGUF

Bronze48

unsloth · Code Generation · from Qwen/Qwen3-Coder-Next

295.8K

downloads

43new

Qwen3-Coder-Next-MLX-6bit

Bronze33

lmstudio-community · Other · from Qwen/Qwen3-Coder-Next

285.6K

downloads

44new

Qwen3.5-9B-int4-AutoRound

Bronze39

Intel · Other · from Qwen/Qwen3.5-9B

283.8K

downloads

45new

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Bronze45

Jackrong · Math & Reasoning · from adapter:Qwen/Qwen3.5-9B

273.4K

downloads

46new

Qwen3-Coder-Next-AWQ-4bit

Bronze39

bullpoint · Code Generation · from Qwen/Qwen3-Coder-Next

272.0K

downloads

47new

Qwen3.5-2B-GGUF

Bronze43

unsloth · VLM · from Qwen/Qwen3.5-2B

271.9K

downloads

48new

Qwen3-0.6B

Bronze39

unsloth · Other · from Qwen/Qwen3-0.6B

257.3K

downloads

49new

Qwen3.5-122B-A10B-NVFP4

Bronze39

txn545 · LLM - General · from Qwen/Qwen3.5-122B-A10B

255.9K

downloads

50new

Qwen_Qwen3.5-35B-A3B-GGUF

Bronze41

bartowski · VLM · from Qwen/Qwen3.5-35B-A3B

255.5K

downloads

51new

Qwen3.5-9B-AWQ-4bit

Bronze38

cyankiwi · VLM · from Qwen/Qwen3.5-9B

251.9K

downloads

52new

OTel-Embedding-8B

Bronze31

farbodtavakkoli · Embeddings · from Qwen/Qwen3-Embedding-8B

244.2K

downloads

53new

Qwen3.5-397B-A17B-NVFP4

Bronze42

nvidia · LLM - General · from Qwen/Qwen3.5-397B-A17B

237.3K

downloads

54new

jina-reranker-m0

Bronze43

jinaai · Other · from Qwen/Qwen2-VL-2B-Instruct

228.6K

downloads

55new

SWE-agent-LM-7B

Bronze35

SWE-bench · Code Generation · from Qwen/Qwen2.5-Coder-7B-Instruct

228.4K

downloads

56new

jina-reranker-v3

Bronze43

jinaai · Other · from Qwen/Qwen3-0.6B

227.2K

downloads

57new

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

Bronze47

Jackrong · VLM · from adapter:Qwen/Qwen3.5-27B

227.1K

downloads

58new

Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Bronze42

Jackrong · Math & Reasoning · from adapter:Qwen/Qwen3.5-4B

226.4K

downloads

59new

TableGPT2-7B

Bronze45

tablegpt · Other · from Qwen/Qwen2.5-7B

223.2K

downloads

60new

Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF

Bronze36

ggml-org · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

215.2K

downloads

61new

Qwen3-0.6B-unsloth-bnb-4bit

Bronze39

unsloth · LLM - General · from Qwen/Qwen3-0.6B

214.1K

downloads

62new

Qwen-Image-Edit-2509-Photo-to-Anime

Bronze43

autoweeb · Image-to-Image · from adapter:Qwen/Qwen-Image-Edit-2509

213.9K

downloads

63new

Qwen2.5-7B-Instruct-bnb-4bit

Bronze38

unsloth · Chat & Assistants · from Qwen/Qwen2.5-7B-Instruct

205.7K

downloads

64new

Qwen_Qwen3.5-4B-GGUF

Bronze38

bartowski · VLM · from Qwen/Qwen3.5-4B

202.7K

downloads

65new

Qwen3-Coder-30B-A3B-Instruct-MLX-4bit

Bronze38

lmstudio-community · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

200.3K

downloads

66new

Qwen3-Coder-30B-A3B-Instruct-MLX-5bit

Bronze35

lmstudio-community · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

199.3K

downloads

67new

Qwen-Image-Edit-2511-Lightning

Bronze46

lightx2v · Image-to-Image · from adapter:Qwen/Qwen-Image-Edit-2511

198.5K

downloads

68new

Qwen3-Coder-Next-AWQ-4bit

Bronze38

cyankiwi · Code Generation · from Qwen/Qwen3-Coder-Next

197.6K

downloads

69new

Qwen3.5-4B-AWQ-4bit

Bronze36

cyankiwi · VLM · from Qwen/Qwen3.5-4B

194.9K

downloads

70new

Qwen3-14B-unsloth-bnb-4bit

Bronze37

unsloth · LLM - General · from Qwen/Qwen3-14B

193.4K

downloads

71new

Qwen3.5-27B-AWQ-4bit

Bronze39

cyankiwi · VLM · from Qwen/Qwen3.5-27B

192.7K

downloads

72new

Qwen3-4B-Instruct-2507-unsloth-bnb-4bit

Bronze37

unsloth · Chat & Assistants · from Qwen/Qwen3-4B-Instruct-2507

190.9K

downloads

73new

jina-code-embeddings-1.5b

Bronze40

jinaai · Embeddings · from Qwen/Qwen2.5-Coder-1.5B

190.4K

downloads

74new

Qwen3-Coder-30B-A3B-Instruct-MLX-8bit

Bronze37

lmstudio-community · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

188.1K

downloads

75new

Qwen3-Coder-30B-A3B-Instruct-MLX-6bit

Bronze34

lmstudio-community · Code Generation · from Qwen/Qwen3-Coder-30B-A3B-Instruct

185.6K

downloads

76new

Qwen3.5-9B

Bronze37

unsloth · VLM · from Qwen/Qwen3.5-9B

183.9K

downloads

77new

Baichuan-M2-32B

Bronze43

baichuan-inc · Chat & Assistants · from Qwen/Qwen2.5-32B

182.4K

downloads

78new

Qwen3-VL-4B-Instruct-MLX-4bit

Bronze35

lmstudio-community · VLM · from Qwen/Qwen3-VL-4B-Instruct

178.7K

downloads

79new

Qwen3.5-397B-A17B-GGUF

Bronze44

unsloth · VLM · from Qwen/Qwen3.5-397B-A17B

177.9K

downloads

80new

Qwen3.5-4B

Bronze37

unsloth · VLM · from Qwen/Qwen3.5-4B

177.0K

downloads

81new

Qwen3-0.6B-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-0.6B

176.0K

downloads

82new

Qwen3-1.7B-GGUF

Bronze35

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-1.7B

175.7K

downloads

83new

Qwen_Qwen3.5-0.8B-GGUF

Bronze36

bartowski · VLM · from Qwen/Qwen3.5-0.8B

175.6K

downloads

84new

Qwen3-14B-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-14B

173.9K

downloads

85new

Qwen3-4B-GGUF

Bronze35

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-4B

173.3K

downloads

86new

Qwen3-8B-GGUF

Bronze35

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-8B

173.1K

downloads

87new

Qwen3-VL-4B-Instruct-MLX-8bit

Bronze30

lmstudio-community · VLM · from Qwen/Qwen3-VL-4B-Instruct

172.5K

downloads

88new

Qwen3-VL-4B-Instruct-MLX-6bit

Bronze30

lmstudio-community · VLM · from Qwen/Qwen3-VL-4B-Instruct

172.2K

downloads

89new

Qwen3-VL-4B-Instruct-MLX-5bit

Bronze30

lmstudio-community · VLM · from Qwen/Qwen3-VL-4B-Instruct

171.9K

downloads

90new

Qwen3.5-35B-A3B-AWQ

Bronze37

QuantTrio · VLM · from Qwen/Qwen3.5-35B-A3B

170.4K

downloads

91new

Qwen2.5-7B

Bronze35

unsloth · LLM - General · from Qwen/Qwen2.5-7B

169.5K

downloads

92new

Qwen3-30B-A3B-GGUF

Bronze33

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-30B-A3B

169.4K

downloads

93new

Qwen3-32B-GGUF

Bronze32

MaziyarPanahi · Role-Play & Characters · from Qwen/Qwen3-32B

169.4K

downloads

94new

RolmOCR

Bronze46

reducto · VLM · from Qwen/Qwen2.5-VL-7B-Instruct

168.9K

downloads

95new

OTel-Reranker-4B

Bronze30

farbodtavakkoli · Other · from Qwen/Qwen3-4B

167.7K

downloads

96new

OTel-LLM-8.2B-IT

Bronze30

farbodtavakkoli · LLM - General · from Qwen/Qwen3-8B

164.4K

downloads

97new

Qwen_Qwen3.5-2B-GGUF

Bronze36

bartowski · VLM · from Qwen/Qwen3.5-2B

162.3K

downloads

98new

Qwen3.5-9B-FP8

Bronze35

lovedheart · VLM · from Qwen/Qwen3.5-9B

161.7K

downloads

99new

Qwen2.5-0.5B-Instruct

Bronze39

Gensyn · Chat & Assistants · from Qwen/Qwen2.5-0.5B

161.3K

downloads

100new

Qwen3-30B-A3B-NVFP4

Bronze38

nvidia · LLM - General · from Qwen/Qwen3-30B-A3B

160.2K

downloads

About the Top Qwen Fine-Tunes Leaderboard

Best fine-tunes built on Alibaba's Qwen family — Qwen2, Qwen2.5, and Qwen3. This leaderboard tracks the top 100 fine-tuned models ranked by downloads, with daily snapshots to monitor how the rankings evolve over time.

Unlike HuggingFace's default model hub, Fine-Tune Catalog filters out pure quantizations and format conversions (repos that simply re-package a model as GGUF, AWQ, GPTQ, or EXL2 without any new training). Fine-tuned models published in quantized formats are still included — what matters is whether new training happened, not the output format.

Methodology

Rankings are based on total all-time download counts from HuggingFace. Downloads reflect real-world adoption — models and datasets that people actually use in production and research, not just stars or hype.

Rankings are snapshotted daily at 6:00 AM UTC. Position changes shown on the leaderboard compare the current snapshot to the previous day's snapshot. All data is sourced directly from the HuggingFace Hub API and processed through our classification pipeline, which uses tag analysis, model card parsing, and naming pattern detection to identify genuine fine-tunes.

Data Sources

  • HuggingFace Hub API — download counts, likes, trending scores, model metadata, and README/model cards
  • Model card parsing — training datasets, training method (LoRA, DPO, SFT, etc.), framework, hardware, and hyperparameters extracted from README files
  • Tag classification — fine-tune detection via `base_model:finetune:*` and `base_model:quantized:*` HuggingFace tags, plus naming pattern analysis

Who Is This For?

This leaderboard is designed for engineers who have already chosen a base model architecture and want to find the best fine-tuned versions available, saving them the time and compute of training from scratch.

Whether you're a beginner exploring what's possible with fine-tuned AI models or an experienced ML engineer looking for the best starting point for your next project, these rankings give you a data-driven way to find the highest quality models without having to wade through thousands of quantizations, format conversions, and abandoned repositories on HuggingFace.

Update Schedule

This leaderboard was last updated on April 3, 2026. Rankings are refreshed daily with the latest download counts, likes, and trending data from HuggingFace. Historical snapshots are preserved to track trends over time — you can see which models are gaining traction and which are losing momentum.