ggml-org AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 158
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 6.6M
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 91.3M
- Total likes
- 2,792
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- 1.4M
Most downloaded
- 1Qwen3.8-27B-GGUFSep 27, 20262M
- 2gemma-4-E4B-it-GGUFJul 26, 2026625.5K
- 3models-movedOct 28, 2025502.5K
- 4embeddinggemma-300M-GGUFApr 29, 2026327.8K
- 5gemma-4-26B-A4B-it-GGUFJul 26, 2026319.1K
- 6gemma-3-1b-it-GGUFMar 12, 2025204.9K
- 7NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFSep 13, 2026192.9K
- 8gpt-oss-20b-GGUFJul 28, 2026155.5K
- 9gpt-oss-120b-GGUFJul 28, 2026144.4K
- 10Qwen3.6-35B-A3B-GGUFJul 16, 2026120.5K
Fastest growing
- 1gemma-4-E4B-it-GGUF+232.4K in 7D625.5K
- 2Qwen3.8-27B-GGUF+201.3K in 7D2M
- 3models-moved+155.8K in 7D502.5K
- 4embeddinggemma-300M-GGUF+76.1K in 7D327.8K
- 5gemma-4-26B-A4B-it-GGUF+74.7K in 7D319.1K
- 6Qwen3.5-0.8B-GGUF+60K in 7D96.6K
- 7gemma-3-1b-it-GGUF+45.3K in 7D204.9K
- 8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF+44.6K in 7D192.9K
- 9gpt-oss-20b-GGUF+31.2K in 7D155.5K
- 10tinygemma3-GGUF+27.8K in 7D104.1K
Recently updated
- 1Muse-Glimmer-30B-GGUFOct 8, 2026285
- 2GLM-5.3-Flash-GGUFOct 8, 20261,935
- 3vocabsOct 7, 20261,900
- 4embeddinggemma-2-GGUFOct 6, 202612.6K
- 5Clef-GGUFOct 5, 202614.2K
- 6Clef-Flash-GGUFOct 5, 202631.1K
- 7Laya-GGUFOct 4, 202611.1K
- 8MiMo-V2.6-Pro-RL-GGUFOct 2, 20261,293
- 9MiMo-V2.6-Pro-MOPD-GGUFOct 2, 20261,422
- 10Bespoke-Nimble-9B-v3-GGUFOct 2, 202614K
All models
| Model | DL 30D | 7D |
|---|---|---|
| Qwen2-VL-2B-Instruct-GGUFggml-org/qwen2-vl-2b-instruct-gguf | 11.2K | +3,744 |
| MiMo-V2.6-Flash-RL-GGUFggml-org/mimo-v2.6-flash-rl-gguf | 10.8K | — |
| Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUFggml-org/qwen3-coder-30b-a3b-instruct-q8_0-gguf | 10.3K | +891 |
| GLM-4.7-Flash-GGUFggml-org/glm-4.7-flash-gguf | 10K | +2,249 |
| DeepSeek-V4-Flash-Vision-Exp-GGUFggml-org/deepseek-v4-flash-vision-exp-gguf | 9,665 | +899 |
| Qwen3-4B-GGUFggml-org/qwen3-4b-gguf | 9,582 | +3,039 |
| Qwen3-4B-Instruct-2507-Q8_0-GGUFggml-org/qwen3-4b-instruct-2507-q8_0-gguf | 9,058 | +555 |
| HunyuanOCR-GGUFggml-org/hunyuanocr-gguf | 8,600 | +2,675 |
| GLM-4.6V-GGUFggml-org/glm-4.6v-gguf | 8,141 | +1,611 |
| moondream2-20250414-GGUFggml-org/moondream2-20250414-gguf | 7,973 | +2,093 |
| Kimi-VL-A3B-Thinking-2506-GGUFggml-org/kimi-vl-a3b-thinking-2506-gguf | 6,773 | +1,300 |
| gemma-3-27b-it-GGUFggml-org/gemma-3-27b-it-gguf | 6,304 | +2,139 |
| Qwen2.5-Coder-1.5B-Q8_0-GGUFggml-org/qwen2.5-coder-1.5b-q8_0-gguf | 6,045 | +1,995 |
| GLM-4.6V-Flash-GGUFggml-org/glm-4.6v-flash-gguf | 5,976 | +655 |
| DeepSeek-V4-Flash-0731-GGUFggml-org/deepseek-v4-flash-0731-gguf | 5,604 | +667 |
| SmolVLM2-256M-Video-Instruct-GGUFggml-org/smolvlm2-256m-video-instruct-gguf | 5,543 | +1,163 |
| Step-3.5-Flash-GGUFggml-org/step-3.5-flash-gguf | 5,462 | +987 |
| gemma-3-4b-it-qat-GGUFggml-org/gemma-3-4b-it-qat-gguf | 4,976 | +1,119 |
| Voxtral-Mini-3B-2507-GGUFggml-org/voxtral-mini-3b-2507-gguf | 4,668 | +1,474 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-GGUFggml-org/nvidia-nemotron-3-nano-30b-a3b-gguf | 4,637 | +1,129 |
| LightOnOCR-2-1B-GGUFggml-org/lightonocr-2-1b-gguf | 4,623 | +940 |
| DeepSeek-OCR-GGUFggml-org/deepseek-ocr-gguf | 4,561 | +1,278 |
| Qwen3-VL-2B-Instruct-GGUFggml-org/qwen3-vl-2b-instruct-gguf | 4,166 | +1,220 |
| Qwen3-Coder-Next-GGUFggml-org/qwen3-coder-next-gguf | 3,866 | +753 |
| dots.ocr-GGUFggml-org/dots.ocr-gguf | 3,819 | +1,000 |