This model was converted to MLX format from Qwen/Qwen3.5-122B-A10B
using mlx-vlm version 0.4.4.
Refer to the original model card for more details on the model.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/Qwen3.5-122B-A10B-mxfp8 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
model-00001-of-00025.safetensors 5.2 GBmodel-00021-of-00025.safetensors 5.2 GBmodel-00017-of-00025.safetensors 5.2 GBmodel-00013-of-00025.safetensors 5.2 GBmodel-00011-of-00025.safetensors 5.2 GBmodel-00007-of-00025.safetensors 5.2 GBmodel-00009-of-00025.safetensors 5.2 GBmodel-00019-of-00025.safetensors 5.2 GBmodel-00015-of-00025.safetensors 5.2 GBmodel-00023-of-00025.safetensors 5.2 GBmodel-00003-of-00025.safetensors 5.2 GBmodel-00005-of-00025.safetensors 5.2 GBmodel-00010-of-00025.safetensors 5.2 GBmodel-00020-of-00025.safetensors 5.2 GBmodel-00016-of-00025.safetensors 5.2 GBmodel-00022-of-00025.safetensors 5.2 GBmodel-00008-of-00025.safetensors 5.2 GBmodel-00014-of-00025.safetensors 5.2 GBmodel-00006-of-00025.safetensors 5.2 GBmodel-00012-of-00025.safetensors 5.2 GBmodel-00002-of-00025.safetensors 5.2 GBmodel-00018-of-00025.safetensors 5.2 GBmodel-00024-of-00025.safetensors 5.2 GBmodel-00004-of-00025.safetensors 5.2 GBmodel-00025-of-00025.safetensors 2.5 GBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo mlx-community/Qwen3.5-122B-A10B-mxfp8 ./model-folderQwen/Qwen3.5-122B-A10B