OpenModelStats

lmstudio-community AI Models

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

Tracked models
406
Downloads 30D
34.2M
Total downloads
258.8M
Total likes
4,079
Gained 7D
—

Most downloaded

  1. 1Qwen3.8-27B-GGUFAug 14, 20261.7M
  2. 2Qwen3.8-27B-MLX-4bitAug 14, 20261.3M
  3. 3gemma-4-E4B-it-MLX-4bitJul 23, 20261.2M
  4. 4gemma-4-E4B-it-MLX-8bitJul 23, 20261.2M
  5. 5gemma-4-E4B-it-MLX-5bitJul 23, 20261.2M
  6. 6gemma-4-E4B-it-MLX-6bitJul 23, 20261.2M
  7. 7Qwen3.8-27B-MLX-8bitAug 14, 20261.2M
  8. 8Qwen3.8-27B-MLX-6bitAug 14, 20261.1M
  9. 9Qwen3.8-27B-MLX-5bitAug 14, 20261.1M
  10. 10Qwen3.6-27B-MLX-8bitJun 2, 2026717.6K

Recently updated

  1. 1Qwen3.8-27B-MLX-8bitAug 14, 20261.2M
  2. 2Qwen3.8-27B-MLX-6bitAug 14, 20261.1M
  3. 3Qwen3.8-27B-MLX-5bitAug 14, 20261.1M
  4. 4Qwen3.8-27B-GGUFAug 14, 20261.7M
  5. 5Qwen3.8-27B-MLX-4bitAug 14, 20261.3M
  6. 6Muse-Glimmer-30B-GGUFAug 12, 2026354.9K
  7. 7NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFAug 11, 202625.8K
  8. 8LFM2.5-2.6B-MLX-8bitAug 5, 20266,556
  9. 9LFM2.5-2.6B-MLX-4bitAug 5, 20261,590
  10. 10LFM2.5-2.6B-GGUFAug 5, 20265,893

All models

All tracked models published by lmstudio-community
ModelDL 30D7D
gemma-4-E2B-it-GGUFlmstudio-community/gemma-4-e2b-it-gguf147.2K—
Qwen3-Coder-Next-MLX-8bitlmstudio-community/qwen3-coder-next-mlx-8bit134.6K—
Qwen2.5-Coder-14B-Instruct-MLX-4bitlmstudio-community/qwen2.5-coder-14b-instruct-mlx-4bit131.3K—
Qwen3-Coder-30B-A3B-Instruct-MLX-8bitlmstudio-community/qwen3-coder-30b-a3b-instruct-mlx-8bit131K—
Qwen3-Coder-30B-A3B-Instruct-MLX-5bitlmstudio-community/qwen3-coder-30b-a3b-instruct-mlx-5bit129.3K—
Qwen3-Coder-30B-A3B-Instruct-MLX-6bitlmstudio-community/qwen3-coder-30b-a3b-instruct-mlx-6bit127.5K—
Qwen3-Coder-Next-MLX-4bitlmstudio-community/qwen3-coder-next-mlx-4bit127.2K—
gpt-oss-20b-GGUFlmstudio-community/gpt-oss-20b-gguf125.8K—
DeepSeek-R1-0528-Qwen3-8B-GGUFlmstudio-community/deepseek-r1-0528-qwen3-8b-gguf123.4K—
Llama-3.2-3B-Instruct-GGUFlmstudio-community/llama-3.2-3b-instruct-gguf123.2K—
Qwen3-Coder-Next-MLX-6bitlmstudio-community/qwen3-coder-next-mlx-6bit121.7K—
Qwen2.5-Coder-14B-Instruct-MLX-8bitlmstudio-community/qwen2.5-coder-14b-instruct-mlx-8bit107K—
Qwen3.5-4B-GGUFlmstudio-community/qwen3.5-4b-gguf106.6K—
Qwen3-VL-4B-Instruct-MLX-4bitlmstudio-community/qwen3-vl-4b-instruct-mlx-4bit104.7K—
Qwen3-VL-4B-Instruct-MLX-8bitlmstudio-community/qwen3-vl-4b-instruct-mlx-8bit101.3K—
Qwen3-VL-4B-Instruct-MLX-6bitlmstudio-community/qwen3-vl-4b-instruct-mlx-6bit100.9K—
Qwen3-VL-4B-Instruct-MLX-5bitlmstudio-community/qwen3-vl-4b-instruct-mlx-5bit100.8K—
Qwen3-VL-8B-Instruct-GGUFlmstudio-community/qwen3-vl-8b-instruct-gguf96.1K—
Qwen2.5-VL-7B-Instruct-GGUFlmstudio-community/qwen2.5-vl-7b-instruct-gguf93.1K—
LFM2-24B-A2B-MLX-4bitlmstudio-community/lfm2-24b-a2b-mlx-4bit92.7K—
GLM-4.6V-Flash-MLX-4bitlmstudio-community/glm-4.6v-flash-mlx-4bit91.7K—
LFM2-24B-A2B-MLX-8bitlmstudio-community/lfm2-24b-a2b-mlx-8bit91.3K—
LFM2-24B-A2B-MLX-6bitlmstudio-community/lfm2-24b-a2b-mlx-6bit91.3K—
LFM2-24B-A2B-MLX-5bitlmstudio-community/lfm2-24b-a2b-mlx-5bit91.2K—
Qwen3-VL-8B-Instruct-MLX-4bitlmstudio-community/qwen3-vl-8b-instruct-mlx-4bit90.5K—