Downloads · 30 days
201
13% of all-time downloads
Qwen3.8-27B-MTP-2bit-MLX
lukaskremla/Qwen3.8-27B-MTP-2bit-MLX
Qwen3.8-27B-MTP-2bit-MLX is a text generation model from lukaskremla. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This repository contains a 2-bit affine quantization of the native Multi-Token Prediction (MTP) tensors extracted from Qwen/Qwen3.8-27B and converted into the standalone MLX drafter format expected by mlx-vlm.
All-time downloads
1.6K
Public
Parameters
425M
153 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors133 MB · 83%
Parameter types
How the weights are stored.
U32425M · 100%
Try a prompt
Model card
From the Hugging Face model README
lukaskremla/Qwen3.8-27B-MTP-2bit-MLX
This repository contains a 2-bit affine quantization of the native Multi-Token Prediction (MTP) tensors extracted from Qwen/Qwen3.8-27B and converted into the standalone MLX drafter format expected by mlx-vlm.
This is not a standalone language model. It must be loaded as the draft model alongside a compatible Qwen3.8-27B target model.
This 2-bit drafter can be used with the 2-bit, 3-bit, 4-bit, 5-bit, 6-bit and 8-bit MLX target models. Quantizations don't need to match.
You can download the vision capable or text-only Qwen 3.8 27B weights in a variety of MLX quantizations 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.
Credits
Converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm version 0.6.13.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5_mtp
- License
- apache-2.0
- Created
- Aug 14, 2026
- Updated
- Aug 15, 2026