Sign up

Shiftedx/Qwen3.8-27B-MLX-MXFP8

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ HF checksums availableupdated today
No torrent yet →

Qwen3.8-27B MLX MXFP8

Vision-enabled MLX conversion of Qwen/Qwen3.8-27B, pinned to revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.

  • Language model: MXFP8, 8-bit, group size 32
  • Vision tower: same-revision BF16 weights
  • Runtime: mlx-vlm 0.6.3 or newer

The Hub's approximately 8.0B safetensors count reflects packed MXFP storage elements; the underlying architecture remains the full 27B model.

Use

python -m mlx_vlm.generate \
  --model Shiftedx/Qwen3.8-27B-MLX-MXFP8 \
  --image image.jpg \
  --prompt "Describe this image."

Text generation and three image-understanding smoke tests passed locally. Quantization can still change behavior, so independently evaluate important use cases. Treat prompts, images, and outputs as untrusted: do not submit secrets, and sandbox tools or generated code with least-privilege access. This conversion adds no telemetry or remote execution.

The upstream Apache-2.0 license and model limitations continue to apply.