Downloads · 30 days
17
7% of all-time downloads
Qwen3-4B-C-Coder-SFT-v1-mlx-4bit
harshpreet931/Qwen3-4B-C-Coder-SFT-v1-mlx-4bit
Qwen3-4B-C-Coder-SFT-v1-mlx-4bit is a text generation model from harshpreet931. 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.
4-bit MLX quantization (4.5 bits/weight) of Qwen3-4B-C-Coder-SFT-v1 for Apple Silicon. ~2.1GB; runs comfortably on 8GB+ unified memory.
All-time downloads
246
Public
Parameters
4B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
Parameter types
How the weights are stored.
U324B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B-C-Coder-SFT-v1 — MLX 4-bit
4-bit MLX quantization (4.5 bits/weight) of Qwen3-4B-C-Coder-SFT-v1 for Apple Silicon. ~2.1GB; runs comfortably on 8GB+ unified memory.
See the main repo for benchmarks, training details, data attribution, and limitations.
pip install mlx-lm
mlx_lm.generate --model harshpreet931/Qwen3-4B-C-Coder-SFT-v1-mlx-4bit \
--prompt "Write a C function int popcount32(unsigned int x) that counts set bits." \
--temp 0.7 --top-p 0.8
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Jul 6, 2026
- Updated
- Jul 6, 2026