Downloads · 30 days
23
4% of all-time downloads
RepublicOfKorokke/Qwen3.5-27B-mlx-lm-mxfp4
Qwen3.5-27B-mlx-lm-mxfp4 is a text generation model from RepublicOfKorokke. 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 MODEL DOES NOT SUPPORT MULTIMODAL<br
Downloads · 30 days
23
4% of all-time downloads
All-time downloads
518
Public
Parameters
26.9B
14.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.3 GB · 100%
How the weights are stored.
U3226.9B · 100%
From the Hugging Face model README
THIS MODEL DOES NOT SUPPORT MULTIMODAL<br>
This model was converted to MLX format from Qwen/Qwen3.5-27B using mlx-lm version 0.30.7.
Conversion Command
$ uv run mlx_lm.convert --hf-path Qwen/Qwen3.5-27B --mlx-path Qwen3.5-27B-mlx-lm-mxfp4 -q --q-mode mxfp4 -q-group-size 32