Downloads · 30 days
14
11% of all-time downloads
Qwen2.5-1.5B-Instruct-MLX-4bit
Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-4bit
Qwen2.5-1.5B-Instruct-MLX-4bit is a text generation model from Irfanuruchi. 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 repository contains an MLX-converted and 4-bit quantized version of Qwen/Qwen2.5-1.5B-Instruct.
All-time downloads
132
Public
Parameters
1.5B
880 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors869 MB · 99%
Parameter types
How the weights are stored.
U321.5B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen2.5-1.5B-Instruct (MLX, 4-bit)
This repository contains an MLX-converted and 4-bit quantized version of
Qwen/Qwen2.5-1.5B-Instruct.
- No fine-tuning or training was performed
- Format conversion + post-training quantization only
- Optimized for Apple Silicon and on-device usage
✅ Recommended default for iPhone
This 4-bit variant is recommended as the default for on-device usage (e.g., iPhone 13 Pro and newer) due to low memory usage and high throughput.
Usage
pip install -U mlx-lm
mlx_lm.generate \
--model Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-4bit \
--prompt "Write a helpful onboarding message for an iOS app in 3 bullet points."
Bench notes (MacBook Pro M3 Pro)
- Prompt tokens: 45
- Generation tokens: 31
- Generation speed: ~134 tokens/sec
- Peak memory: ~0.945 GB
Related models
- 8-bit variant (higher quality):
https://huggingface.co/Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-8bit
- Task
- Text Generation
- Library
- mlx
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026