Independent MXFP8 MLX conversion of
AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16, pinned at a6775a9a8ebb65cab3f707b4ab087fc7aa698634.
This is a community conversion, not an official AEON-7 or Qwen release.
This package adds the pinned source checkpoint's 15 native BF16 MTP tensors to the paired vision MLX body. Tensor parity, strict MTPLX inspection, a local AR/D1/D2/D3 tune, and deterministic text/vision smokes passed.
mtp-faster-than-ar
Runtime speed and acceptance depend on host, prompt, context, and MTPLX version;
benchmark locally before selecting speculative depth.mtplx inspect --json --require-mtp <local-path-or-repo-id>
mtplx tune --model <local-path-or-repo-id> --depths 1,2,3 --json
This is an experimental quantization of an abliterated, intentionally unaligned checkpoint. Quantization does not restore safety alignment. The source publisher warns that the model can produce unsafe or illegal material and places downstream safety and legal responsibility on operators. Review the source model card before use and add access controls, logging, moderation, and human review appropriate to your deployment.
python -m mlx_vlm.generate --model <repo-or-path> --image image.jpg --prompt "Describe this image." --max-tokens 256
model-00003-of-00014.safetensors 2.1 GBmodel-00005-of-00014.safetensors 2.1 GBmodel-00009-of-00014.safetensors 2.1 GBmodel-00002-of-00014.safetensors 2.1 GBmodel-00007-of-00014.safetensors 2.1 GBmodel-00004-of-00014.safetensors 2.1 GBmodel-00008-of-00014.safetensors 2.1 GBmodel-00010-of-00014.safetensors 2.1 GBmodel-00001-of-00014.safetensors 2.1 GBmodel-00006-of-00014.safetensors 2.1 GBmodel-00014-of-00014.safetensors 2.0 GBmodel-00012-of-00014.safetensors 1.7 GBmodel-00011-of-00014.safetensors 1.5 GBmodel-00013-of-00014.safetensors 1.3 GBmodel-vision-00001-of-00001.safetensors 921 MB有文件?提交种子。
提交种子