Modelpublic

lukaskremla/Qwen3.8-27B-5bit-MLX

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

0likes90downloads

Model Card

This quantization preserves the model's BF16 vision tower. For a text-only version check lukaskremla/Qwen3.8-27B-5bit-MLX-TextOnly.

You can download MTP heads separately from this collection Qwen 3.8 27B MLX-Quants (Vision, Text-Only & MTP).

Hugging Face might render incorrect parameter counts for this model, it is a common display bug for MLX quants.

Converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm version 0.6.13.