OpenModelStats

hugging-quants AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
12
Downloads 30D
486.9K
Total downloads
25.8M
Total likes
515
Gained 7D
90.2K

Most downloaded

  1. 1Meta-Llama-3.1-8B-Instruct-AWQ-INT4Aug 7, 2024179.6K
  2. 2Meta-Llama-3.1-70B-Instruct-AWQ-INT4Aug 7, 2024165.7K
  3. 3Llama-3.2-1B-Instruct-Q4_K_M-GGUFSep 25, 202458.4K
  4. 4Llama-3.2-3B-Instruct-Q4_K_M-GGUFSep 25, 202438K
  5. 5Meta-Llama-3.1-8B-Instruct-GPTQ-INT4Aug 7, 20248,721
  6. 6Llama-3.2-1B-Instruct-Q8_0-GGUFSep 25, 20247,923
  7. 7gemma-2-9b-it-AWQ-INT4Oct 17, 20246,188
  8. 8Mixtral-8x7B-Instruct-v0.1-AWQ-INT4Oct 7, 20244,606
  9. 9Llama-3.2-3B-Instruct-Q8_0-GGUFSep 25, 20242,048
  10. 10Meta-Llama-3.1-405B-Instruct-AWQ-INT4Sep 13, 20241,112

Fastest growing

  1. 1Meta-Llama-3.1-70B-Instruct-AWQ-INT4+44K in 7D165.7K
  2. 2Meta-Llama-3.1-8B-Instruct-AWQ-INT4+16.2K in 7D179.6K
  3. 3Llama-3.2-1B-Instruct-Q4_K_M-GGUF+14.9K in 7D58.4K
  4. 4Llama-3.2-3B-Instruct-Q4_K_M-GGUF+8,518 in 7D38K
  5. 5Llama-3.2-1B-Instruct-Q8_0-GGUF+2,547 in 7D7,923
  6. 6gemma-2-9b-it-AWQ-INT4+1,725 in 7D6,188
  7. 7Meta-Llama-3.1-8B-Instruct-GPTQ-INT4+817 in 7D8,721
  8. 8Llama-3.2-3B-Instruct-Q8_0-GGUF+567 in 7D2,048
  9. 9Meta-Llama-3.1-405B-Instruct-AWQ-INT4+450 in 7D1,112
  10. 10Mixtral-8x7B-Instruct-v0.1-AWQ-INT4+420 in 7D4,606

Recently updated

  1. 1gemma-2-9b-it-AWQ-INT4Oct 17, 20246,188
  2. 2Mixtral-8x7B-Instruct-v0.1-AWQ-INT4Oct 7, 20244,606
  3. 3Llama-3.2-1B-Instruct-Q4_K_M-GGUFSep 25, 202458.4K
  4. 4Llama-3.2-1B-Instruct-Q8_0-GGUFSep 25, 20247,923
  5. 5Llama-3.2-3B-Instruct-Q4_K_M-GGUFSep 25, 202438K
  6. 6Llama-3.2-3B-Instruct-Q8_0-GGUFSep 25, 20242,048
  7. 7Meta-Llama-3.1-405B-Instruct-AWQ-INT4Sep 13, 20241,112
  8. 8Meta-Llama-3.1-8B-Instruct-AWQ-INT4Aug 7, 2024179.6K
  9. 9Meta-Llama-3.1-70B-Instruct-GPTQ-INT4Aug 7, 2024359
  10. 10Meta-Llama-3.1-405B-Instruct-GPTQ-INT4Aug 7, 2024218

All models

All tracked models published by hugging-quants
ModelDL 30D7D
Meta-Llama-3.1-8B-Instruct-AWQ-INT4hugging-quants/meta-llama-3.1-8b-instruct-awq-int4179.6K+16.2K
Meta-Llama-3.1-70B-Instruct-AWQ-INT4hugging-quants/meta-llama-3.1-70b-instruct-awq-int4165.7K+44K
Llama-3.2-1B-Instruct-Q4_K_M-GGUFhugging-quants/llama-3.2-1b-instruct-q4_k_m-gguf58.4K+14.9K
Llama-3.2-3B-Instruct-Q4_K_M-GGUFhugging-quants/llama-3.2-3b-instruct-q4_k_m-gguf38K+8,518
Meta-Llama-3.1-8B-Instruct-GPTQ-INT4hugging-quants/meta-llama-3.1-8b-instruct-gptq-int48,721+817
Llama-3.2-1B-Instruct-Q8_0-GGUFhugging-quants/llama-3.2-1b-instruct-q8_0-gguf7,923+2,547
gemma-2-9b-it-AWQ-INT4hugging-quants/gemma-2-9b-it-awq-int46,188+1,725
Mixtral-8x7B-Instruct-v0.1-AWQ-INT4hugging-quants/mixtral-8x7b-instruct-v0.1-awq-int44,606+420
Llama-3.2-3B-Instruct-Q8_0-GGUFhugging-quants/llama-3.2-3b-instruct-q8_0-gguf2,048+567
Meta-Llama-3.1-405B-Instruct-AWQ-INT4hugging-quants/meta-llama-3.1-405b-instruct-awq-int41,112+450
Meta-Llama-3.1-70B-Instruct-GPTQ-INT4hugging-quants/meta-llama-3.1-70b-instruct-gptq-int4359+73
Meta-Llama-3.1-405B-Instruct-GPTQ-INT4hugging-quants/meta-llama-3.1-405b-instruct-gptq-int4218+0