inferencerlabs on Hugging Face: downloads and rankings
inferencerlabs has 63 tracked models, downloaded 25,255 times in the last 30 days and 243,693 times in total. inferencerlabs Wrapped: the last 12 months.
Models by downloads in the last 30 days
- inferencerlabs/Kimi-K3.1-Pro-MLXse 3.6K downloads, image text to text
- inferencerlabs/Mistral-Large-4-1T-A52B-MLX-Q3i 2.3K downloads, image text to text
- inferencerlabs/DeepSeek-V4.1-Flash-1017-MLXse 1.7K downloads, image text to text
- inferencerlabs/DeepSeek-V4.1-Flash-MLX-Q4i 1.7K downloads, image text to text
- inferencerlabs/DeepSeek-V4.1-Flash-1017-MLXs 1.1K downloads, image text to text
- inferencerlabs/GLM-5.3-Flash-MTP-MLX 813 downloads, text generation
- inferencerlabs/MiniMax-M3.1-Flash-MLX 805 downloads, image text to text
- inferencerlabs/Muse-Spark-Open-816B-A42B-MLX-Q4i 782 downloads, image text to text
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q6s 688 downloads, image text to text
- inferencerlabs/GLM-5.3-Flash-MLX-Q9 616 downloads, image text to text
- inferencerlabs/Qwen3-Coder-Next-MLX-Q9 603 downloads, text generation
- inferencerlabs/GLM-5.3-MLX-Q4i 547 downloads, text generation
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q9se 527 downloads, image text to text
- inferencerlabs/DeepSeek-V4-Flash-MLX-Q2i 463 downloads, text generation
- inferencerlabs/GLM-5.3-MTP-MLX 463 downloads, text generation
- inferencerlabs/GLM-5.2-MLX-Q4i 455 downloads, text generation
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4s 449 downloads, image text to text
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q9s 446 downloads, image text to text
- inferencerlabs/DeepSeek-V4.1-Flash-MLX-Q9 445 downloads, image text to text
- inferencerlabs/DeepSeek-V4-Pro-MTP-MLX 414 downloads, text generation
- inferencerlabs/MiMo-V2.6-Pro-RL-MLX-Q9 405 downloads, image text to text
- inferencerlabs/DeepSeek-V4.1-Flash-1017-MTP-MLX 388 downloads, text generation
- inferencerlabs/Qwen3.8-Flash-Next-MTP-MLX 379 downloads, image text to text
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q9 346 downloads, image text to text
- inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 345 downloads, text generation
- inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX 340 downloads, image text to text
- inferencerlabs/GLM-5.2-MTP-MLX 303 downloads, image text to text
- inferencerlabs/Kimi-K2.7-Code-MLX-Q3i 244 downloads, image text to text
- inferencerlabs/Qwen3.6-35B-A3B-MLX-Q9 224 downloads, image text to text
- inferencerlabs/Qwen3.8-Flash-Next-MLX-Q4i 209 downloads, image text to text
- inferencerlabs/MiMo-V2.6-Flash-RL-MLX-Q9 206 downloads, image text to text
- inferencerlabs/DeepSeek-V4-Flash-0731-MLX 201 downloads, text generation
- inferencerlabs/Mistral-Small-4-119B-2603-MLX-Q9 200 downloads, text generation
- inferencerlabs/Qwen3.8-27B-MLX-Q9 169 downloads, image text to text
- inferencerlabs/Qwen3.5-9B-LM-MLX-Q4 169 downloads, text generation
- inferencerlabs/DeepSeek-V4-Flash-MTP-MLX 159 downloads, text generation
- inferencerlabs/gemma-4-26B-A4B-MTP-MLX 158 downloads, image text to text
- inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX 152 downloads, text generation
- inferencerlabs/Atria-Dawn-Preview-MLX-Q4i 147 downloads, text generation
- inferencerlabs/Kolibri-MLX-Q9 133 downloads, text generation
- inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i 120 downloads, text generation
- inferencerlabs/Qwen3.8-27B-MTP-MLX 119 downloads, image text to text
- inferencerlabs/gemma-4-31B-MTP-MLX 118 downloads, image text to text
- inferencerlabs/Qwen3.5-4B-LM-MLX-Q4 114 downloads, text generation
- inferencerlabs/gemma-4-31B-MLX-Q9 113 downloads, image text to text
- inferencerlabs/Qwen3.6-35B-A3B-MTP-MLX 112 downloads, image text to text
- inferencerlabs/granite-vision-4.1-4b-MLX-Q9 107 downloads, image text to text
- inferencerlabs/Ling-3.0-flash-Q9 98 downloads, text generation
- inferencerlabs/Bonsai-4B-MLX-Q2 82 downloads, text generation
- inferencerlabs/Inkling-Small-MLX-Q9 76 downloads, image text to text
- inferencerlabs/Bonsai-8B-MLX-Q2 74 downloads, text generation
- inferencerlabs/Muse-Glimmer-30B-MLX-Q9 47 downloads, image text to text
- inferencerlabs/gemma-4-26B-A4B-MLX-Q9 46 downloads, image text to text
- inferencerlabs/Qwen3.6-27B-MLX-Q9 43 downloads, image text to text
- inferencerlabs/Qwen3.5-9B-LM-MLX-Q9 36 downloads, text generation
- inferencerlabs/Qwen3.5-4B-LM-MLX-Q9 36 downloads, text generation
- inferencerlabs/gemma-4-12B-Q9 34 downloads, any to any
- inferencerlabs/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-MLX-Q9 26 downloads, any to any
- inferencerlabs/gemma-4-E2B-MLX-Q9 25 downloads, any to any
- inferencerlabs/Qwen3.5-0.8B-LM-MLX-Q9 23 downloads, text generation
- inferencerlabs/gemma-4-E4B-MLX-Q9 20 downloads, any to any
- inferencerlabs/Qwen3.6-27B-MTP-MLX 16 downloads, image text to text
- inferencerlabs/Hydrogen-1.0-MLX-Q4 5 downloads, text generation
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.