Downloads · 30 days
24
21% of all-time downloads
Qwen3.8-27B-6bit-FP16-MTPLX
SWiesmann/Qwen3.8-27B-6bit-FP16-MTPLX
Qwen3.8-27B-6bit-FP16-MTPLX is a machine learning model from SWiesmann. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from Qwen/Qwen3.8-27B.
All-time downloads
114
Public
Parameters
4.2B
16 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16 GB · 100%
Parameter types
How the weights are stored.
U323.4B · 80%
Model card
From the Hugging Face model README
Qwen3.8-27B-6bit-FP16-MTPLX
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX).
Forged with MTPLX Forge from
Qwen/Qwen3.8-27B.
Verification
- Best depth: D3
- Multiplier vs autoregressive baseline: 1.52×
- Verified on: Apple M2 Max
- Sampler: temperature 0.6 · top_p 0.95 · top_k 20
See mtplx_runtime.json for the full verification record.
Usage
# MTPLX picks this model up automatically when downloaded:
mtplx pull <owner>/Qwen3.8-27B-6bit-FP16-MTPLX
mtplx start chat
License
See LICENSE.
- Type
- qwen3_5
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026