Microsoft's compact 3.8B Phi-4 SLM designed for on-device inference; released alongside Phi-4-multimodal under an MIT license with 128K context support.
@hn_f2aea1
about 1 month ago
I saw pretty good reasoning quality with phi-4-mini. But alright - I’ll still run some tests with qwen2.5-coder and plan to add support for it next. Would be great to compare them side by side in practical shell tasks. Thanks so much for the pointer!
@hn_6abdf8
3 months ago
Thanks so much! Was the model too big to run locally? That’s one of the reasons I went with phi-4-mini - surprisingly high quality for its size and speed. It handled multi-step reasoning, math, structured data extraction, and code pretty well, all on modest hardware. Phi-1.5 / Phi-2 (quantized versions) also run on raspberry pi as others have demonstrated.
@hn_014e14
3 months ago
fair jab - haha; if we’re gonna go small, might as well go fully local and open. At least with phi-4-mini you don’t need an API key, and you can tweak/replace the model easily