Top VLM Fine-Tunes

Best fine-tuned vision-language models for image understanding, OCR, and visual reasoning.

Last updated April 3, 2026 · Updated daily

Qwen3.5-35B-A3B-GGUF by unsloth holds the #1 position with 1.7M downloads, ahead of InternVL2-2B at 1.4M.

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

The gap between #1 and #100 is 1.7M vs 58.9K 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

InternVL2-2B

Bronze46

OpenGVLab · VLM · from merge:internlm/internlm2-chat-1_8b

1.4M

downloads

🥉new

Qwen3.5-9B-GGUF

Silver51

unsloth · VLM · from Qwen/Qwen3.5-9B

1.3M

downloads

4new

gemma-3-4b-it-qat-4bit

Bronze39

mlx-community · VLM · from OpenGVLab/InternVL3-1B-Instruct

968.6K

downloads

5new

Qwen3.5-27B-GGUF

Silver50

unsloth · VLM · from Qwen/Qwen3.5-27B

836.3K

downloads

6new

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

Silver50

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

771.6K

downloads

7new

gemma-3-27b-it-AWQ-INT4

Bronze39

pytorch · VLM · from google/gemma-3-27b-it

714.3K

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

InternVL3_5-GPT-OSS-20B-A4B-Preview-HF

Bronze39

OpenGVLab · VLM · from merge:openai/gpt-oss-20b

589.1K

downloads

11new

Qwen3.5-4B-GGUF

Bronze47

unsloth · VLM · from Qwen/Qwen3.5-4B

580.3K

downloads

12new

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

Bronze38

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

561.1K

downloads

13new

Molmo2-8B

Bronze46

allenai · VLM · from Qwen/Qwen3-8B

529.7K

downloads

14new

Qwen3.5-4B-FP8

Bronze34

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

516.2K

downloads

15new

InternVL2-1B

Bronze44

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

502.8K

downloads

16new

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

Silver53

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

487.4K

downloads

17new

Qwen3.5-122B-A10B-GGUF

Bronze46

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

450.6K

downloads

18new

InternVL2-8B

Bronze46

OpenGVLab · VLM · from merge:internlm/internlm2_5-7b-chat

429.6K

downloads

19new

olmOCR-2-7B-1025

Bronze45

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

401.1K

downloads

20new

Qwen3.5-27B-AWQ

Bronze41

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

393.0K

downloads

21new

gemma-3-4b-it-GGUF

Bronze40

lmstudio-community · VLM · from google/gemma-3-4b-it

370.9K

downloads

22new

PaddleOCR-VL-1.5

Bronze48

PaddlePaddle · VLM · from baidu/ERNIE-4.5-0.3B-Paddle

335.9K

downloads

23new

Nanonets-OCR2-3B

Bronze48

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

331.2K

downloads

24new

Qwen3.5-122B-A10B-NVFP4

Bronze42

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

325.7K

downloads

25new

Qwen3.5-0.8B-GGUF

Bronze44

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

310.4K

downloads

26new

DeepSeek-OCR-2

Bronze40

unsloth · VLM · from deepseek-ai/DeepSeek-OCR-2

306.7K

downloads

27new

Qwen3.5-9B-AWQ

Bronze37

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

297.1K

downloads

28new

Qwen3.5-2B-GGUF

Bronze43

unsloth · VLM · from Qwen/Qwen3.5-2B

271.9K

downloads

29new

Qwen_Qwen3.5-35B-A3B-GGUF

Bronze41

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

255.5K

downloads

30new

Qwen3.5-9B-AWQ-4bit

Bronze38

cyankiwi · VLM · from Qwen/Qwen3.5-9B

251.9K

downloads

31new

gemma-3-12b-it-quantized-W4A16

Bronze36

abhishekchohan · VLM · from google/gemma-3-12b-it

228.3K

downloads

32new

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

Bronze47

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

227.1K

downloads

33new

GLM-4.6V-Flash-MLX-4bit

Bronze32

lmstudio-community · VLM · from zai-org/GLM-4.6V-Flash

208.5K

downloads

34new

GLM-4.6V-Flash-MLX-8bit

Bronze30

lmstudio-community · VLM · from zai-org/GLM-4.6V-Flash

204.2K

downloads

35new

Qwen_Qwen3.5-4B-GGUF

Bronze38

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

202.7K

downloads

36new

GLM-4.6V-Flash-MLX-6bit

Bronze30

lmstudio-community · VLM · from zai-org/GLM-4.6V-Flash

202.6K

downloads

37new

Qwen3.5-4B-AWQ-4bit

Bronze36

cyankiwi · VLM · from Qwen/Qwen3.5-4B

194.9K

downloads

38new

Qwen3.5-27B-AWQ-4bit

Bronze39

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

192.7K

downloads

39new

gemma-3-27b-it-GPTQ-4b-128g

Bronze40

ISTA-DASLab · VLM · from google/gemma-3-27b-it

186.0K

downloads

40new

Qwen3.5-9B

Bronze37

unsloth · VLM · from Qwen/Qwen3.5-9B

183.9K

downloads

41new

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

Bronze35

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

178.7K

downloads

42new

Qwen3.5-397B-A17B-GGUF

Bronze44

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

177.9K

downloads

43new

Qwen3.5-4B

Bronze37

unsloth · VLM · from Qwen/Qwen3.5-4B

177.0K

downloads

44new

Qwen_Qwen3.5-0.8B-GGUF

Bronze36

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

175.6K

downloads

45new

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

Bronze30

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

172.5K

downloads

46new

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

Bronze30

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

172.2K

downloads

47new

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

Bronze30

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

171.9K

downloads

48new

Qwen3.5-35B-A3B-AWQ

Bronze37

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

170.4K

downloads

49new

RolmOCR

Bronze46

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

168.9K

downloads

50new

Qwen_Qwen3.5-2B-GGUF

Bronze36

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

162.3K

downloads

51new

Qwen3.5-9B-FP8

Bronze35

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

161.7K

downloads

52new

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

Bronze44

Jackrong · VLM · from adapter:Qwen/Qwen3.5-9B

158.2K

downloads

53new

Qwen3-VL-32B-Instruct-AWQ

Bronze36

QuantTrio · VLM · from Qwen/Qwen3-VL-32B-Instruct

153.8K

downloads

54new

gemma-3n-E4B-it-MLX-4bit

Bronze30

lmstudio-community · VLM · from google/gemma-3n-E4B-it

151.2K

downloads

55new

gemma-3n-E4B-it-MLX-bf16

Bronze32

lmstudio-community · VLM · from google/gemma-3n-E4B-it

147.5K

downloads

56new

gemma-3n-E4B-it-MLX-8bit

Bronze30

lmstudio-community · VLM · from google/gemma-3n-E4B-it

147.4K

downloads

57new

olmOCR-2-7B-1025-FP8

Bronze44

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

147.0K

downloads

58new

gemma-3n-E4B-it-MLX-6bit

Bronze30

lmstudio-community · VLM · from google/gemma-3n-E4B-it

146.9K

downloads

59new

Qwen3.5-122B-A10B-AWQ-4bit

Bronze38

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

146.5K

downloads

60new

Qwen3.5-2B

Bronze36

unsloth · VLM · from Qwen/Qwen3.5-2B

146.2K

downloads

61new

Huihui-Qwen3.5-27B-abliterated

Bronze42

huihui-ai · VLM · from Qwen/Qwen3.5-27B

138.6K

downloads

62new

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

Bronze33

lmstudio-community · VLM · from Qwen/Qwen3-VL-8B-Instruct

127.0K

downloads

63new

Qwen_Qwen3.5-9B-GGUF

Bronze39

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

124.0K

downloads

64new

gemma-3-12b-it-qat-4bit

Bronze37

mlx-community · VLM · from OpenGVLab/InternVL3-1B-Instruct

123.5K

downloads

65new

Qwen3.5-27B-NVFP4

Bronze38

apolo13x · VLM · from Qwen/Qwen3.5-27B

123.3K

downloads

66new

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

Bronze33

lmstudio-community · VLM · from Qwen/Qwen3-VL-8B-Instruct

121.9K

downloads

67new

gemma-3-27b-it-GGUF

Bronze43

unsloth · VLM · from google/gemma-3-27b-it

121.5K

downloads

68new

Qwen3-VL-8B-Instruct-MLX-5bit

Bronze29

lmstudio-community · VLM · from Qwen/Qwen3-VL-8B-Instruct

120.7K

downloads

69new

Qwen3-VL-8B-Instruct-MLX-6bit

Bronze29

lmstudio-community · VLM · from Qwen/Qwen3-VL-8B-Instruct

120.2K

downloads

70new

Qwen3-VL-4B-Instruct-GGUF

Bronze39

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

117.3K

downloads

71new

Qwen3.5-9B-MLX-4bit

Bronze40

mlx-community · VLM · from Qwen/Qwen3.5-9B

116.8K

downloads

72new

gemma-3-27b-it-qat-4bit

Bronze37

mlx-community · VLM · from OpenGVLab/InternVL3-1B-Instruct

116.6K

downloads

73new

gemma-3-12b-it-GGUF

Bronze42

unsloth · VLM · from google/gemma-3-12b-it

107.1K

downloads

74new

Qwen3.5-0.8B

Bronze35

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

106.5K

downloads

75new

gemma-4-26B-A4B-it-GGUF

Bronze42

unsloth · VLM · from google/gemma-4-26B-A4B-it

99.2K

downloads

76new

Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

Bronze40

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

98.3K

downloads

77new

Qwen_Qwen3.5-27B-GGUF

Bronze39

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

94.1K

downloads

78new

Qwen_Qwen3.5-397B-A17B-GGUF

Bronze33

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

89.9K

downloads

79new

Qwen3.5-35B-A3B-NVFP4

Bronze31

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

89.5K

downloads

80new

Molmo2-4B

Bronze38

allenai · VLM · from Qwen/Qwen3-4B-Instruct-2507

85.6K

downloads

81new

gemma-4-31B-it-GGUF

Bronze40

unsloth · VLM · from google/gemma-4-31B-it

83.9K

downloads

82new

Qwen3.5-27B-AWQ-BF16-INT8

Bronze33

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

80.6K

downloads

83new

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

Bronze35

cyankiwi · VLM · from Qwen/Qwen3-VL-8B-Instruct

79.5K

downloads

84new

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

Bronze41

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

77.4K

downloads

85new

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

Bronze34

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

75.2K

downloads

86new

Qwen3-VL-2B-Instruct-unsloth-bnb-4bit

Bronze32

unsloth · VLM · from Qwen/Qwen3-VL-2B-Instruct

72.2K

downloads

87new

Qwen3.5-35B-A3B-heretic-v2-GGUF

Bronze38

llmfan46 · VLM · from Qwen/Qwen3.5-35B-A3B

70.4K

downloads

88new

Qwen_Qwen3.5-122B-A10B-GGUF

Bronze35

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

63.8K

downloads

89new

Qwen3.5-397B-A17B-MLX-8bit

Bronze27

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

63.5K

downloads

90new

Huihui-Qwen3.5-35B-A3B-abliterated

Bronze42

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

62.8K

downloads

91new

gemma-3-4b-it-GGUF

Bronze41

unsloth · VLM · from google/gemma-3-4b-it

62.4K

downloads

92new

R-4B

Bronze41

YannQi · VLM · from Qwen/Qwen3-4B

61.9K

downloads

93new

Qwen3-VL-8B-Instruct-GGUF

Bronze37

unsloth · VLM · from Qwen/Qwen3-VL-8B-Instruct

61.9K

downloads

94new

InternVL2_5-2B

Bronze36

OpenGVLab · VLM · from merge:internlm/internlm2_5-1_8b-chat

61.3K

downloads

95new

Bee-8B-RL

Bronze39

Open-Bee · VLM · from Qwen/Qwen3-8B

60.9K

downloads

96new

gemma-3-12b-it-GGUF

Bronze37

lmstudio-community · VLM · from google/gemma-3-12b-it

60.5K

downloads

97new

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

Bronze27

lmstudio-community · VLM · from Qwen/Qwen3-VL-30B-A3B-Instruct

60.3K

downloads

98new

OpenCUA-7B

Bronze36

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

60.2K

downloads

99new

Cosmos-Reason2-8B

Bronze41

nvidia · VLM · from Qwen/Qwen3-VL-8B-Instruct

59.2K

downloads

100new

gemma-4-E4B-it-GGUF

Bronze39

unsloth · VLM · from google/gemma-4-E4B-it

58.9K

downloads

About the Top VLM Fine-Tunes Leaderboard

Best fine-tuned vision-language models for image understanding, OCR, and visual reasoning. 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 developers working in specific AI domains who need the best model for their particular use case — whether that's language understanding, computer vision, image generation, voice synthesis, or semantic search.

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.

Explore more rankings: Most Downloaded Fine-Tunes · Most Liked Fine-Tunes · Highest Quality Fine-Tunes · Top Uncensored Models · Top LLM Fine-Tunes · Top Image Generation Fine-Tunes and 16 more leaderboards