Downloads · 30 days
59
8% of all-time downloads
Qwen3.8-27B-MTP-MLX-6bit
adrianmurray/Qwen3.8-27B-MTP-MLX-6bit
Qwen3.8-27B-MTP-MLX-6bit is a text generation model from adrianmurray. 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 artifact is the native multi-token prediction head extracted from the official Qwen/Qwen3.8-27B checkpoint and quantized to affine 6-bit MLX weights. It is bound to a matching target model and is used as a specul…
All-time downloads
765
Public
Parameters
425M
345 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
Parameter types
How the weights are stored.
U32425M · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B native MTP MLX 6-bit
This artifact is the native multi-token prediction head extracted from the
official Qwen/Qwen3.8-27B checkpoint and quantized to affine 6-bit MLX
weights. It is bound to a matching target model and is used as a speculative
draft by Qwen Prime Runtime and DFlash verification.
It is not a separately trained DFlash diffusion model. Speculative verification remains lossless with respect to the configured target decoding policy; speed depends on draft acceptance and workload.
Identity
- Source model:
Qwen/Qwen3.8-27B - Source revision:
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0 - Target model:
Qwen/Qwen3.8-27B - Quantization: affine 6-bit, group size 64
- MTP layers: one
- Weight SHA-256:
0af49c2c931f9f98c6beb2a85cae899a1c839647aae28b18e9187af53340fab2
qwen-prime-runtime doctor verifies the source/target binding and the complete
weight hash before the artifact is used.
Reproduction
uv run python -m harness.trainer.export_qwen38_mtp \
--source /path/to/Qwen3.8-27B \
--output /path/to/Qwen3.8-27B-MTP-MLX-6bit \
--source-revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
License
The original model is Copyright 2026 Alibaba Cloud and is licensed under Apache License 2.0. This directory includes that license and a modification notice. This independent derivative is not endorsed by Alibaba Cloud or the Qwen team.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_8_mtp
- License
- apache-2.0
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026