OpenModelStats

lmstudio-community AI Models

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

Tracked models
449
Downloads 30D
38.6M
Total downloads
322.8M
Total likes
4,756
Gained 7D
9.9M

Most downloaded

  1. 1Qwen3.8-27B-MLX-4bitAug 14, 20264.2M
  2. 2Qwen3.8-27B-MLX-8bitAug 14, 20264M
  3. 3Qwen3.8-27B-MLX-6bitAug 14, 20264M
  4. 4Qwen3.8-27B-MLX-5bitAug 14, 20264M
  5. 5Qwen3.8-27B-GGUFAug 14, 20261.2M
  6. 6gemma-4-E4B-it-MLX-4bitJul 23, 20261.1M
  7. 7gemma-4-E4B-it-MLX-8bitJul 23, 20261.1M
  8. 8gemma-4-E4B-it-MLX-6bitJul 23, 20261.1M
  9. 9gemma-4-E4B-it-MLX-5bitJul 23, 20261.1M
  10. 10Qwen3.5-9B-MLX-4bitJun 2, 2026608.2K

Fastest growing

  1. 1Qwen3.8-27B-MLX-4bit+1.1M in 7D4.2M
  2. 2Qwen3.8-27B-MLX-8bit+1M in 7D4M
  3. 3Qwen3.8-27B-MLX-6bit+1M in 7D4M
  4. 4Qwen3.8-27B-MLX-5bit+1M in 7D4M
  5. 5Qwen3.8-27B-GGUF+313.9K in 7D1.2M
  6. 6gemma-4-E4B-it-MLX-4bit+281.6K in 7D1.1M
  7. 7gemma-4-E4B-it-MLX-8bit+274.7K in 7D1.1M
  8. 8gemma-4-E4B-it-MLX-6bit+273.9K in 7D1.1M
  9. 9gemma-4-E4B-it-MLX-5bit+273.7K in 7D1.1M
  10. 10Qwen3.5-9B-MLX-4bit+151.6K in 7D608.2K

Recently updated

  1. 1Qwen3.8-Flash-Next-GGUFAug 27, 202616.3K
  2. 2granite-4.2-8b-MLX-8bitAug 25, 20264,020
  3. 3granite-4.2-8b-MLX-6bitAug 25, 2026586
  4. 4granite-4.2-30b-MLX-8bitAug 25, 20261,645
  5. 5granite-4.2-8b-MLX-4bitAug 25, 20262,606
  6. 6granite-4.2-30b-MLX-6bitAug 25, 2026398
  7. 7granite-4.2-30b-MLX-4bitAug 25, 2026895
  8. 8granite-4.2-30b-GGUFAug 25, 20261,814
  9. 9granite-4.2-3b-MLX-8bitAug 25, 2026799
  10. 10granite-4.2-3b-MLX-6bitAug 25, 2026188

All models

All tracked models published by lmstudio-community
ModelDL 30D7D
Hermes-4-70B-GGUFlmstudio-community/hermes-4-70b-gguf8,210+2,326
KAT-Dev-MLX-8bitlmstudio-community/kat-dev-mlx-8bit8,198+482
Qwen2.5-VL-72B-Instruct-GGUFlmstudio-community/qwen2.5-vl-72b-instruct-gguf7,809+812
gemma-2-9b-it-GGUFlmstudio-community/gemma-2-9b-it-gguf7,755+1,855
Phi-4-mini-instruct-GGUFlmstudio-community/phi-4-mini-instruct-gguf7,581+1,111
dolphin-2.8-mistral-7b-v02-GGUFlmstudio-community/dolphin-2.8-mistral-7b-v02-gguf7,579+1,956
granite-4.0-h-tiny-GGUFlmstudio-community/granite-4.0-h-tiny-gguf7,361+1,957
Qwen2.5-0.5B-Instruct-MLX-4bitlmstudio-community/qwen2.5-0.5b-instruct-mlx-4bit7,297+1,927
Codestral-22B-v0.1-GGUFlmstudio-community/codestral-22b-v0.1-gguf6,922+2,169
rnj-1-instruct-GGUFlmstudio-community/rnj-1-instruct-gguf6,871+1,764
Qwen2.5-Coder-3B-Instruct-GGUFlmstudio-community/qwen2.5-coder-3b-instruct-gguf6,843+1,834
Mistral-Small-3.2-24B-Instruct-2506-GGUFlmstudio-community/mistral-small-3.2-24b-instruct-2506-gguf6,701+1,858
Magistral-Small-2506-MLX-4bitlmstudio-community/magistral-small-2506-mlx-4bit6,541+1,875
magistral-small-2506-mlx-bf16lmstudio-community/magistral-small-2506-mlx-bf166,528+1,873
gemma-3n-E4B-it-text-GGUFlmstudio-community/gemma-3n-e4b-it-text-gguf6,346+1,777
gemma-3-27b-it-GGUFlmstudio-community/gemma-3-27b-it-gguf6,321+1,594
Qwen2.5-Coder-1.5B-Instruct-GGUFlmstudio-community/qwen2.5-coder-1.5b-instruct-gguf6,308+1,519
Qwen2.5-Coder-32B-Instruct-GGUFlmstudio-community/qwen2.5-coder-32b-instruct-gguf6,089+2,900
Phi-4-reasoning-plus-GGUFlmstudio-community/phi-4-reasoning-plus-gguf5,916+1,772
Qwen2.5-VL-32B-Instruct-GGUFlmstudio-community/qwen2.5-vl-32b-instruct-gguf5,863+1,033
Meta-Llama-3-8B-Instruct-GGUFlmstudio-community/meta-llama-3-8b-instruct-gguf5,774+1,633
Qwen3-30B-A3B-GGUFlmstudio-community/qwen3-30b-a3b-gguf5,759+2,175
Qwen2.5-14B-Instruct-1M-GGUFlmstudio-community/qwen2.5-14b-instruct-1m-gguf5,665+1,522
QwQ-32B-GGUFlmstudio-community/qwq-32b-gguf5,492+1,385
Ministral-3-8B-Instruct-2512-GGUFlmstudio-community/ministral-3-8b-instruct-2512-gguf5,454+1,265