Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-8bit

Qwen2.5-1.5B-Instruct (MLX, 8-bit)

This repository contains an MLX-converted and 8-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

---

Usage

pip install -U mlx-lm

mlx_lm.generate \
  --model Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-8bit \
  --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: 100
• Generation speed: ~74.7 tokens/sec
• Peak memory: ~1.717 GB

---

Related models

• 4-bit variant (recommended default for iPhone):
  https://huggingface.co/Irfanuruchi/Qwen2.5-1.5B-Instruct-MLX-4bit