Downloads · 30 days
14
8% of all-time downloads
Qwen2.5-3B-Instruct-4bit-mlx
TheAndyRoberts/Qwen2.5-3B-Instruct-4bit-mlx
Qwen2.5-3B-Instruct-4bit-mlx is a text generation model from TheAndyRoberts. 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.
MLX 4-bit quantization of Qwen/Qwen2.5-3B-Instruct, converted with mlx-lm for Apple Silicon.
All-time downloads
176
Public
Parameters
3.1B
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 99%
Parameter types
How the weights are stored.
U323.1B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen2.5-3B-Instruct-4bit-mlx
MLX 4-bit quantization of Qwen/Qwen2.5-3B-Instruct,
converted with mlx-lm for Apple Silicon.
Use
pip install mlx-lm
mlx_lm.generate --model TheAndyRoberts/Qwen2.5-3B-Instruct-4bit-mlx \
--prompt "Your prompt here" --max-tokens 100
Conversion details
- Source:
Qwen/Qwen2.5-3B-Instruct(fp16) - Quantization: 4-bit (default
mlx_lm.convert -qsettings, group size 64) - Tooling:
mlx-lmVersion: 0.29.1
License
Apache 2.0 (inherited from base model)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen2
- License
- apache-2.0
- Created
- May 16, 2026
- Updated
- May 16, 2026