Downloads · 30 days
90
9% of all-time downloads
Qwen3.5-27B-mlx-lm-3bit
RepublicOfKorokke/Qwen3.5-27B-mlx-lm-3bit
Qwen3.5-27B-mlx-lm-3bit 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
All-time downloads
979
Public
Parameters
26.9B
11.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors11.8 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 100%
Try a prompt
Base models
Model card
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-3bit -q --q-bits 3
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026