Top Llama Fine-Tunes

Best fine-tunes built on Meta's Llama family — Llama 2, Llama 3, Llama 3.1, and Llama 3.3.

Last updated April 3, 2026 · Updated daily

Llama-3.2-1B-Instruct-FP8-dynamic by RedHatAI holds the #1 position with 1.5M downloads, ahead of Llama-3.2-1B-Instruct-Q8_0-GGUF at 852.8K.

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

The gap between #1 and #100 is 1.5M vs 24.3K downloads, showing significant concentration at the top.

🥇new

Llama-3.2-1B-Instruct-FP8-dynamic

Bronze38

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

1.5M

downloads

🥈new

Llama-3.2-1B-Instruct-Q8_0-GGUF

Bronze44

hugging-quants · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

852.8K

downloads

🥉new

Llama-3.2-1B-Instruct-FP8

Bronze37

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

851.5K

downloads

4new

Llama-3.2-3B-Instruct-GGUF

Bronze47

bartowski · Chat & Assistants · from meta-llama/Llama-3.2-3B-Instruct

562.6K

downloads

5new

llama-3.3-70b-instruct-awq

Bronze42

casperhansen · Chat & Assistants · from meta-llama/Llama-3.1-70B

538.1K

downloads

6new

Llama-3.3-70B-Instruct-AWQ

Bronze38

kosbu · Chat & Assistants · from meta-llama/Llama-3.3-70B-Instruct

471.9K

downloads

7new

vntl-llama3-8b-v2-gguf

Bronze39

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

458.6K

downloads

8new

TinyLlama-1.1B-Chat-v0.3-GPTQ

Bronze38

TheBloke · Code Generation · from TinyLlama/TinyLlama-1.1B-Chat-v0.3

402.0K

downloads

9new

Meta-Llama-3.1-8B-Instruct-FP8

Bronze41

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

315.9K

downloads

10new

Meta-Llama-3.1-8B-Instruct

Bronze43

unsloth · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

309.0K

downloads

11new

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

Bronze43

unsloth · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

303.4K

downloads

12new

Llama-3.1-8B-Instruct

Bronze37

unsloth · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

292.8K

downloads

13new

Meta-Llama-3.1-8B-Instruct-GGUF

Bronze46

bartowski · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

246.1K

downloads

14new

Llama-3.1-8B-Instruct-FP8

Bronze40

nvidia · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

235.0K

downloads

15new

Meta-Llama-3.1-8B-FP8

Bronze37

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

224.0K

downloads

16new

Meta-Llama-3.1-8B-Instruct-GGUF

Bronze39

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.1-8B-Instruct

198.0K

downloads

17new

Llama-3.2-3B-Instruct

Bronze42

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-3B-Instruct

189.5K

downloads

18new

watt-tool-8B

Bronze43

watt-ai · Other · from meta-llama/Llama-3.1-8B-Instruct

188.1K

downloads

19new

Llama-3.2-1B-Instruct

Bronze42

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

175.3K

downloads

20new

Llama-2-7B-Chat-GGUF

Bronze46

TheBloke · Chat & Assistants · from meta-llama/Llama-2-7b-chat-hf

151.2K

downloads

21new

Meta-Llama-3-8B-Instruct-GGUF

Bronze41

MaziyarPanahi · Role-Play & Characters · from meta-llama/Meta-Llama-3-8B-Instruct

115.2K

downloads

22new

Llama-3.3-70B-Instruct-GGUF

Bronze37

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.3-70B-Instruct

114.6K

downloads

23new

Llama-3.2-1B-Instruct-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.2-1B-Instruct

114.3K

downloads

24new

Meta-Llama-3.1-70B-Instruct-GGUF

Bronze38

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.1-70B-Instruct

113.2K

downloads

25new

Llama-3.2-3B-Instruct-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.2-3B-Instruct

112.9K

downloads

26new

firefunction-v2-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from fireworks-ai/llama-3-firefunction-v2

111.8K

downloads

27new

Meta-Llama-3.1-405B-Instruct-GGUF

Bronze36

MaziyarPanahi · Role-Play & Characters · from meta-llama/Llama-3.1-405B-Instruct

110.2K

downloads

28new

TinyLlama-1.1B-Chat-v1.0-GGUF

Bronze43

TheBloke · Other · from TinyLlama/TinyLlama-1.1B-Chat-v1.0

109.6K

downloads

29new

Meta-Llama-3.3-70B-Instruct-AWQ-INT4

Bronze38

ibnzterrell · Chat & Assistants · from meta-llama/Llama-3.3-70B-Instruct

107.3K

downloads

30new

Hermes-3-Llama-3.1-8B

Bronze44

NousResearch · Role-Play & Characters · from meta-llama/Llama-3.1-8B

106.9K

downloads

31new

Llama-3.2-1B-Instruct-unsloth-bnb-4bit

Bronze32

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

106.6K

downloads

32new

tada-3b-ml

Bronze42

HumeAI · TTS · from meta-llama/Llama-3.2-3B

103.0K

downloads

33new

Llama-3.1-8B-Instruct-NVFP4

Bronze34

nvidia · Other · from meta-llama/Llama-3.1-8B-Instruct

102.5K

downloads

34new

Llama-3.2-3B-Instruct-unsloth-bnb-4bit

Bronze35

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-3B-Instruct

101.5K

downloads

35new

Llama-3.2-1B-Instruct-GGUF

Bronze42

bartowski · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

95.8K

downloads

36new

Llama-3.3-70B-Instruct-NVFP4

Bronze38

nvidia · Other · from meta-llama/Llama-3.3-70B-Instruct

92.0K

downloads

37new

Llama-3.2-1B-Instruct-GGUF

Bronze39

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

89.9K

downloads

38new

llama-3-8b-bnb-4bit

Bronze42

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

86.4K

downloads

39new

Llama-3.2-1B

Bronze39

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

78.6K

downloads

40new

llama2_7b_lora-arc_challenge

Bronze28

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

73.0K

downloads

41new

llama2_7b_lora-arc_easy

Bronze28

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

69.0K

downloads

42new

tada-1b

Bronze42

HumeAI · TTS · from meta-llama/Llama-3.2-1B

68.1K

downloads

43new

TinyLlama-1.1B-Chat-v0.3-AWQ

Bronze31

TheBloke · Code Generation · from TinyLlama/TinyLlama-1.1B-Chat-v0.3

63.7K

downloads

44new

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

Bronze31

unsloth · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

61.4K

downloads

45new

Llama-4-Scout-17B-16E-Instruct-NVFP4

Bronze36

nvidia · Other · from meta-llama/Llama-4-Scout-17B-16E-Instruct

60.7K

downloads

46new

Skywork-Reward-Llama-3.1-8B-v0.2

Bronze37

Skywork · Other · from meta-llama/Llama-3.1-8B-Instruct

60.6K

downloads

47new

Llama-3.2-3B-Instruct-FP8

Bronze32

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.2-3B-Instruct

60.1K

downloads

48new

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

Bronze39

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

58.1K

downloads

49new

llama2_7b_lora-openbookqa

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

58.0K

downloads

50new

TinyLlama-1.1B-Chat-v1.0-GPTQ

Bronze34

TheBloke · Code Generation · from TinyLlama/TinyLlama-1.1B-Chat-v1.0

54.4K

downloads

51new

llama2_7b_lora-common_gen

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

54.4K

downloads

52new

Llama-3.2-3B-Instruct-bnb-4bit

Bronze36

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-3B-Instruct

54.2K

downloads

53new

Llama-4-Scout-17B-16E-Instruct-FP8

Bronze34

nvidia · Other · from meta-llama/Llama-4-Scout-17B-16E-Instruct

54.2K

downloads

54new

Meta-Llama-3.1-70B-Instruct-FP8

Bronze37

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.1-70B-Instruct

53.0K

downloads

55new

Dolphin3.0-Llama3.1-8B-GGUF

Bronze40

dphn · Other · from meta-llama/Llama-3.1-8B

52.3K

downloads

56new

llama2_7b_lora-cosmos_qa

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

49.6K

downloads

57new

llama2_7b_lora-copa

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

47.4K

downloads

58new

Meta-Llama-3.1-8B-Instruct-GGUF

Bronze41

lmstudio-community · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

46.6K

downloads

59new

llama2_7b_lora-multirc

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

46.3K

downloads

60new

Hermes-3-Llama-3.1-8B-q4f16_1-MLC

Bronze27

mlc-ai · Other · from NousResearch/Hermes-3-Llama-3.1-8B

44.4K

downloads

61new

llama2_7b_lora-natural_questions

Bronze27

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

43.4K

downloads

62new

llama2_7b_lora-anli_r1

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

42.4K

downloads

63new

Llama-4-Scout-17B-16E-Instruct-AWQ

Bronze31

kishizaki-sci · Other · from meta-llama/Llama-4-Scout-17B-16E-Instruct

42.1K

downloads

64new

Llama-4-Scout-17B-16E-Instruct-GGUF

Bronze39

unsloth · VLM · from meta-llama/Llama-4-Scout-17B-16E-Instruct

41.1K

downloads

65new

tiny-random-Llama-3-lora

Bronze26

llamafactory · Other · from adapter:llamafactory/tiny-random-Llama-3

40.6K

downloads

66new

llama2_7b_lora-dart

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

40.6K

downloads

67new

Llama-4-Scout-17B-16E-Instruct-FP8-dynamic

Bronze35

RedHatAI · VLM · from meta-llama/Llama-4-Scout-17B-16E-Instruct

39.9K

downloads

68new

Llama3-OpenBioLLM-8B

Bronze40

aaditya · Chat & Assistants · from meta-llama/Meta-Llama-3-8B

39.2K

downloads

69new

Llama-3.2-1B-Instruct-Q4_K_M-GGUF

Bronze34

hugging-quants · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

38.9K

downloads

70new

Llama-3.2-1B-FP8

Bronze26

RedHatAI · Other · from meta-llama/Llama-3.2-1B

38.8K

downloads

71new

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

Bronze41

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

37.8K

downloads

72new

llama2_7b_lora-drop

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

35.4K

downloads

73new

llama2_7b_lora-wmt16_translate_deen

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

35.4K

downloads

74new

Llama-3.1-8B-Instruct-FP8-KV

Bronze31

amd · Other · from meta-llama/Llama-3.1-8B-Instruct

35.2K

downloads

75new

llama2_7b_lora-wmt16_translate_csen

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

34.4K

downloads

76new

Meta-Llama-3.1-8B-Instruct-quantized.w4a16

Bronze35

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

34.3K

downloads

77new

llama2_7b_lora-glue_mrpc

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

33.9K

downloads

78new

Llama-3.3-70B-Instruct-FP8

Bronze34

nvidia · Other · from meta-llama/Llama-3.3-70B-Instruct

32.4K

downloads

79new

Llama-3.3-70B-Instruct-FP8-dynamic

Bronze33

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.3-70B-Instruct

30.6K

downloads

80new

Llama-3.2-1B-Instruct-bnb-4bit

Bronze34

unsloth · Chat & Assistants · from meta-llama/Llama-3.2-1B-Instruct

30.1K

downloads

81new

llama2_7b_lora-trivia_qa

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

30.0K

downloads

82new

Meta-Llama-3.1-8B-Instruct-GGUF

Bronze33

SanctumAI · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

30.0K

downloads

83new

llama2_7b_lora-web_nlg_en

Bronze26

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

29.1K

downloads

84new

Llama-2-7B-GPTQ

Bronze37

TheBloke · LLM - General · from meta-llama/Llama-2-7b-hf

29.0K

downloads

85new

Llama-4-Scout-17B-16E-Instruct-quantized.w4a16

Bronze32

RedHatAI · VLM · from meta-llama/Llama-4-Scout-17B-16E-Instruct

28.7K

downloads

86new

Llama-3.1-70B-heretic-lora-i1-GGUF

Bronze25

mradermacher · Other · from opensynthesis/Llama-3.1-70B-heretic-lora

28.3K

downloads

87new

Llama-3.2-3B

Bronze33

unsloth · LLM - General · from meta-llama/Llama-3.2-3B

28.3K

downloads

88new

llama2_7b_lora-anli_r2

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

28.0K

downloads

89new

llama2_7b_lora-bool_q

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

27.1K

downloads

90new

Llama-4-Maverick-17B-128E-Instruct-FP8

Bronze27

RedHatAI · VLM · from meta-llama/Llama-4-Maverick-17B-128E-Instruct

26.8K

downloads

91new

Llama-3.1-8B-Instruct-unsloth-bnb-4bit

Bronze29

unsloth · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

26.6K

downloads

92new

llama2_7b_lora-wmt16_translate_fien

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

26.6K

downloads

93new

Meta-Llama-3.1-8B-Instruct-FP8-dynamic

Bronze31

RedHatAI · Chat & Assistants · from meta-llama/Llama-3.1-8B-Instruct

26.2K

downloads

94new

llama2_7b_lora-sst2

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

26.1K

downloads

95new

llama2_7b_lora-mnli_matched

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

25.3K

downloads

96new

Llama-3.2-3B-Instruct-abliterated-GGUF

Bronze31

QuantFactory · Other · from meta-llama/Llama-3.2-3B-Instruct

24.8K

downloads

97new

Llama-3.1-8B-Instruct-heretic-i1-GGUF

Bronze27

mradermacher · Other · from p-e-w/Llama-3.1-8B-Instruct-heretic

24.7K

downloads

98new

llama2_7b_lora-definite_pronoun_resolution

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

24.7K

downloads

99new

llama2_7b_lora-paws_wiki

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

24.3K

downloads

100new

llama2_7b_lora-yelp_polarity_reviews

Bronze25

Styxxxx · Other · from adapter:meta-llama/Llama-2-7b-hf

24.3K

downloads

About the Top Llama Fine-Tunes Leaderboard

Best fine-tunes built on Meta's Llama family — Llama 2, Llama 3, Llama 3.1, and Llama 3.3. 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.