Top LLM Fine-Tunes

Best fine-tuned large language models for text generation, chat, code, and reasoning.

Last updated April 3, 2026 · Updated daily

indonesian-roberta-base-posp-tagger by w11wo holds the #1 position with 2.5M downloads, ahead of gemma-2-2b-it-GGUF at 1.5M.

The top 10 is dominated by w11wo, bartowski, covalenthq. This is the first snapshot — future updates will track position changes and emerging trends.

The gap between #1 and #100 is 2.5M vs 36.6K downloads, showing significant concentration at the top.

🥇new

indonesian-roberta-base-posp-tagger

Bronze43

w11wo · LLM - General · from flax-community/indonesian-roberta-base

2.5M

downloads

🥈new

gemma-2-2b-it-GGUF

Bronze47

bartowski · LLM - General · from google/gemma-2-2b-it

1.5M

downloads

🥉new

cryptoNER

Bronze41

covalenthq · LLM - General · from FacebookAI/xlm-roberta-base

857.6K

downloads

4new

roberta-base-squad2

Silver52

deepset · LLM - General · from FacebookAI/roberta-base

832.7K

downloads

5new

gpt-oss-20b-MXFP4-Q8

Bronze42

mlx-community · LLM - General · from openai/gpt-oss-20b

540.6K

downloads

6new

vntl-llama3-8b-v2-gguf

Bronze39

lmg-anon · LLM - General · from rinna/llama-3-youko-8b

458.6K

downloads

7new

LFM2-24B-A2B-MLX-4bit

Bronze35

lmstudio-community · LLM - General · from LiquidAI/LFM2-24B-A2B

442.1K

downloads

8new

LFM2-24B-A2B-MLX-6bit

Bronze35

lmstudio-community · LLM - General · from LiquidAI/LFM2-24B-A2B

435.8K

downloads

9new

LFM2-24B-A2B-MLX-8bit

Bronze34

lmstudio-community · LLM - General · from LiquidAI/LFM2-24B-A2B

435.0K

downloads

10new

LFM2-24B-A2B-MLX-5bit

Bronze32

lmstudio-community · LLM - General · from LiquidAI/LFM2-24B-A2B

433.7K

downloads

11new

deberta-v3-large-zeroshot-v2.0

Bronze45

MoritzLaurer · LLM - General · from microsoft/deberta-v3-large

407.5K

downloads

12new

OTel-LLM-1.7B-IT

Bronze32

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

396.4K

downloads

13new

OTel-LLM-1B-IT

Bronze32

farbodtavakkoli · LLM - General · from google/gemma-3-1b-it

393.8K

downloads

14new

mistral-7b-v0.3-bnb-4bit

Bronze40

unsloth · LLM - General · from mistralai/Mistral-7B-v0.3

378.3K

downloads

15new

OTel-LLM-0.6B-IT

Bronze32

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

377.2K

downloads

16new

Qwen3-14B-NVFP4

Bronze36

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

366.8K

downloads

17new

DeepSeek-R1-0528-Qwen3-8B-MLX-4bit

Bronze37

lmstudio-community · LLM - General · from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

349.8K

downloads

18new

GLM-4.7-Flash-FP8-Dynamic

Bronze40

unsloth · LLM - General · from zai-org/GLM-4.7-Flash

337.8K

downloads

19new

GLM-4.7-Flash-MLX-8bit

Bronze38

lmstudio-community · LLM - General · from zai-org/GLM-4.7-Flash

335.0K

downloads

20new

DeepSeek-R1-0528-Qwen3-8B-MLX-8bit

Bronze38

lmstudio-community · LLM - General · from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

333.8K

downloads

21new

GLM-4.7-Flash-MLX-6bit

Bronze37

lmstudio-community · LLM - General · from zai-org/GLM-4.7-Flash

327.6K

downloads

22new

OTel-LLM-270M-IT

Bronze32

farbodtavakkoli · LLM - General · from google/gemma-3-270m-it

326.8K

downloads

23new

OTel-LLM-4B-IT

Bronze31

farbodtavakkoli · LLM - General · from google/gemma-3-4b-it

321.6K

downloads

24new

mdeberta-v3-base-squad2

Bronze46

timpal0l · LLM - General · from microsoft/mdeberta-v3-base

311.9K

downloads

25new

gpt-oss-20b-GGUF

Bronze48

unsloth · LLM - General · from openai/gpt-oss-20b

297.6K

downloads

26new

Qwen3.5-122B-A10B-NVFP4

Bronze39

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

255.9K

downloads

27new

GLM-4.7-Flash-AWQ-4bit

Bronze41

cyankiwi · LLM - General · from zai-org/GLM-4.7-Flash

252.5K

downloads

28new

Qwen3.5-397B-A17B-NVFP4

Bronze42

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

237.3K

downloads

29new

bert-base-NER-Russian

Bronze39

Gherman · LLM - General · from google-bert/bert-base-multilingual-cased

236.1K

downloads

30new

distilbert-NER

Bronze41

dslim · LLM - General · from distilbert/distilbert-base-cased

229.7K

downloads

31new

GLM-4.7-Flash-GGUF

Bronze47

unsloth · LLM - General · from zai-org/GLM-4.7-Flash

226.3K

downloads

32new

Meta-Llama-3.1-8B-FP8

Bronze37

RedHatAI · LLM - General · from meta-llama/Llama-3.1-8B

224.0K

downloads

33new

Qwen3-0.6B-unsloth-bnb-4bit

Bronze39

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

214.1K

downloads

34new

sbert_punc_case_ru

Bronze40

kontur-ai · LLM - General · from ai-forever/sbert_large_nlu_ru

197.7K

downloads

35new

gpt-oss-20b

Bronze40

unsloth · LLM - General · from openai/gpt-oss-20b

193.4K

downloads

36new

Qwen3-14B-unsloth-bnb-4bit

Bronze37

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

193.4K

downloads

37new

Jan-nano-AWQ

Bronze33

warshanks · LLM - General · from Menlo/Jan-nano

172.5K

downloads

38new

gpt-oss-20b-unsloth-bnb-4bit

Bronze39

unsloth · LLM - General · from openai/gpt-oss-20b

171.3K

downloads

39new

Qwen2.5-7B

Bronze35

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

169.5K

downloads

40new

OTel-LLM-12B-Safety

Bronze30

farbodtavakkoli · LLM - General · from google/gemma-3-12b-it

166.2K

downloads

41new

OTel-LLM-8.2B-IT

Bronze30

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

164.4K

downloads

42new

modernbert-ner-conll2003

Bronze33

IsmaelMousa · LLM - General · from answerdotai/ModernBERT-base

162.3K

downloads

43new

OTel-LLM-12B-IT

Bronze30

farbodtavakkoli · LLM - General · from google/gemma-3-12b-it

161.7K

downloads

44new

GLM-4.7-Flash-NVFP4

Bronze41

GadflyII · LLM - General · from zai-org/GLM-4.7-Flash

161.4K

downloads

45new

Qwen3-30B-A3B-NVFP4

Bronze38

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

160.2K

downloads

46new

cerebras_GLM-4.5-Air-REAP-82B-A12B-GGUF

Bronze39

bartowski · LLM - General · from cerebras/GLM-4.5-Air-REAP-82B-A12B

156.6K

downloads

47new

Qwen3-1.7B-unsloth-bnb-4bit

Bronze36

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

155.8K

downloads

48new

gpt-oss-120b-BF16

Bronze34

unsloth · LLM - General · from openai/gpt-oss-120b

121.2K

downloads

49new

GLM-4.7-Flash

Bronze36

unsloth · LLM - General · from zai-org/GLM-4.7-Flash

120.5K

downloads

50new

gpt-oss-20b-BF16

Bronze38

unsloth · LLM - General · from openai/gpt-oss-20b

114.0K

downloads

51new

gpt-oss-120b-GGUF

Bronze43

unsloth · LLM - General · from openai/gpt-oss-120b

111.9K

downloads

52new

Qwen3-32B-NVFP4

Bronze36

nvidia · LLM - General · from Qwen/Qwen3-32B

105.6K

downloads

53new

T5_Paraphrase_Paws

Bronze38

Vamsi · LLM - General · from google-t5/t5-base

102.9K

downloads

54new

granite-4.0-h-tiny-AWQ-4bit

Bronze30

cyankiwi · LLM - General · from ibm-granite/granite-4.0-h-tiny

100.8K

downloads

55new

GLM-4.7-Flash-REAP-23B-A3B

Bronze39

cerebras · LLM - General · from zai-org/GLM-4.7-Flash

95.4K

downloads

56new

NVIDIA-Nemotron-3-Super-120B-A12B-GGUF

Bronze40

unsloth · LLM - General · from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

94.1K

downloads

57new

bert-base-NER

Bronze30

Xenova · LLM - General · from dslim/bert-base-NER

92.7K

downloads

58new

distilbert_finetuned_ai4privacy_v2

Bronze36

Isotonic · LLM - General · from distilbert/distilbert-base-uncased

92.6K

downloads

59new

Qwen3-8B

Bronze36

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

90.5K

downloads

60new

DeepSeek-R1-Distill-Qwen-1.5B-GGUF

Bronze41

unsloth · LLM - General · from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

90.3K

downloads

61new

OTel-LLM-14B-IT

Bronze28

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

87.0K

downloads

62new

OTel-LLM-24B-IT

Bronze28

farbodtavakkoli · LLM - General · from LiquidAI/LFM2-24B-A2B

87.0K

downloads

63new

OTel-LLM-27B-IT

Bronze28

farbodtavakkoli · LLM - General · from google/gemma-3-27b-it

86.4K

downloads

64new

llama-3-8b-bnb-4bit

Bronze42

unsloth · LLM - General · from meta-llama/Meta-Llama-3-8B

86.4K

downloads

65new

OTel-LLM-20B-IT

Bronze28

farbodtavakkoli · LLM - General · from openai/gpt-oss-20b

86.1K

downloads

66new

Qwen3-4B-Base

Bronze32

unsloth · LLM - General · from Qwen/Qwen3-4B-Base

85.1K

downloads

67new

Qwen3-Embedding-0.6B-4bit-DWQ

Bronze33

mlx-community · LLM - General · from Qwen/Qwen3-Embedding-0.6B

84.6K

downloads

68new

Qwen2.5-0.5B-unsloth-bnb-4bit

Bronze31

unsloth · LLM - General · from Qwen/Qwen2.5-0.5B

81.6K

downloads

69new

Llama-3.2-1B

Bronze39

unsloth · LLM - General · from meta-llama/Llama-3.2-1B

78.6K

downloads

70new

Qwen3-4B-unsloth-bnb-4bit

Bronze36

unsloth · LLM - General · from Qwen/Qwen3-4B

77.4K

downloads

71new

qmd-query-expansion-1.7B-gguf

Bronze35

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

73.7K

downloads

72new

DeepSeek-R1-0528-Qwen3-8B-GGUF

Bronze38

lmstudio-community · LLM - General · from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

73.0K

downloads

73new

gemma-3-270m-it-GGUF

Bronze41

unsloth · LLM - General · from google/gemma-3-270m-it

65.7K

downloads

74new

Qwen3-4B-GGUF

Bronze41

unsloth · LLM - General · from Qwen/Qwen3-4B

64.7K

downloads

75new

bpmn-information-extraction-v2

Bronze34

jtlicardo · LLM - General · from google-bert/bert-base-cased

62.5K

downloads

76new

MiniMax-M2.5-GGUF

Bronze41

unsloth · LLM - General · from MiniMaxAI/MiniMax-M2.5

60.5K

downloads

77new

gemma-3-1b-it-qat-4bit

Bronze31

mlx-community · LLM - General · from google/gemma-3-1b-it

59.1K

downloads

78new

gpt-oss-120b-MLX-8bit

Bronze34

lmstudio-community · LLM - General · from openai/gpt-oss-120b

59.0K

downloads

79new

bart-large-mnli-yahoo-answers

Bronze34

joeddav · LLM - General · from facebook/bart-large-mnli

58.8K

downloads

80new

Meta-Llama-3.1-8B-bnb-4bit

Bronze39

unsloth · LLM - General · from meta-llama/Llama-3.1-8B

58.1K

downloads

81new

gemma-2-2b-it

Bronze30

Efficient-Large-Model · LLM - General · from google/gemma-2-2b

56.2K

downloads

82new

Qwen3-0.6B-GGUF

Bronze40

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

55.7K

downloads

83new

gpt-oss-120b

Bronze35

unsloth · LLM - General · from openai/gpt-oss-120b

55.5K

downloads

84new

DeepSeek-R1-0528-Qwen3-8B-GGUF

Bronze43

unsloth · LLM - General · from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

53.7K

downloads

85new

Qwen3-1.7B-4bit

Bronze31

mlx-community · LLM - General · from Qwen/Qwen3-1.7B

51.3K

downloads

86new

bge-m3-zeroshot-v2.0

Bronze38

MoritzLaurer · LLM - General · from BAAI/bge-m3-retromae

51.0K

downloads

87new

gemma-3-1b-it-GGUF

Bronze38

unsloth · LLM - General · from google/gemma-3-1b-it

48.1K

downloads

88new

GLM-4.7-Flash-AWQ

Bronze32

QuantTrio · LLM - General · from zai-org/GLM-4.7-Flash

46.9K

downloads

89new

gemma-2-9b-it-GGUF

Bronze41

bartowski · LLM - General · from google/gemma-2-9b-it

46.6K

downloads

90new

deberta-v3-base-zeroshot-v2.0

Bronze33

MoritzLaurer · LLM - General · from microsoft/deberta-v3-base

42.6K

downloads

91new

Qwen3-8B-GGUF

Bronze39

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

41.3K

downloads

92new

Qwen3-30B-A3B-AWQ

Bronze33

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

41.1K

downloads

93new

TheDrummer_Cydonia-24B-v4.2.0-GGUF

Bronze34

bartowski · LLM - General · from TheDrummer/Cydonia-24B-v4.2.0

40.9K

downloads

94new

mobilebert-uncased-mnli

Bronze29

Xenova · LLM - General · from typeform/mobilebert-uncased-mnli

40.6K

downloads

95new

Qwen2.5-1.5B-unsloth-bnb-4bit

Bronze29

unsloth · LLM - General · from Qwen/Qwen2.5-1.5B

40.0K

downloads

96new

gemma-2-9b-it-GGUF

Bronze32

SanctumAI · LLM - General · from google/gemma-2-9b-it

39.7K

downloads

97new

DeepSeek-R1-Distill-Llama-8B-GGUF

Bronze41

unsloth · LLM - General · from deepseek-ai/DeepSeek-R1-Distill-Llama-8B

37.8K

downloads

98new

Qwen3-14B-MLX-4bit

Bronze30

lmstudio-community · LLM - General · from Qwen/Qwen3-14B

37.2K

downloads

99new

DeepSeek-V3.2-NVFP4

Bronze33

nvidia · LLM - General · from deepseek-ai/DeepSeek-V3.2

37.2K

downloads

100new

macbert4mdcspell_v1

Bronze28

Macropodus · LLM - General · from hfl/chinese-macbert-base

36.6K

downloads

About the Top LLM Fine-Tunes Leaderboard

Best fine-tuned large language models for text generation, chat, code, and 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.