You can deploy this model and start earning money today!

Irfanuruchi/
Phi-4-mini-instruct-MLX-4bit

Name: Phi-4-mini-instruct-MLX-4bit
Availability: InStock

Views

No views yet

Phi-4-mini-instruct (MLX 4-bit)

This is a 4-bit MLX quantized version of microsoft/Phi-4-mini-instruct, optimized for Apple Silicon and local / on-device inference.

Benchmarks were collected on macOS (M3 Pro).
iPhone / iPad performance will vary depending on hardware and memory.

bash

mlx_lm.generate \
  --model Irfanuruchi/Phi-4-mini-instruct-MLX-4bit \
  --prompt "Give me 5 short offline assistant tips." \
  --max-tokens 120

Original model license applies. See microsoft/Phi-4-mini-instruct.