Hugging Face · #258

microsoft/Phi-3.5-mini-instruct

microsoft/Phi-3.5-mini-instruct is a 3.8B text-generation model on Hugging Face. Run locally: llama-cli -hf microsoft/Phi-3.5-mini-instruct or ollama run hf.co/microsoft/Phi-3.5-mini-instruct. 1,281 Hugging Face likes (#258 in this directory).

Model
https://huggingface.co/microsoft/Phi-3.5-mini-instruct
Author
microsoft (org)
Likes
1,281
Downloads (30 days)
371,898
Task
text-generation
Library
transformers
License
mit
Parameters
3.8B
Gated
No
Created
2024-08-16
Last modified
2025-12-10
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf microsoft/Phi-3.5-mini-instruct

Ollama

ollama run hf.co/microsoft/Phi-3.5-mini-instruct

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run microsoft/Phi-3.5-mini-instruct only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology