Phi-3.5-mini-instruct — Q4_K_M GGUF (CodeRoast redistribution)

Status: frozen. From Tamys Action v3.0.0 and engine 1.10.12 on, Tamys no longer downloads this model: narration is opt-in, on the user's own model key. The files here stay pinned and unchanged, never removed, for the older releases that fetch them (the Sift Action v2, engine 1.10.11 and earlier) and for the coderoast-server courtesy profile.

GGUF quantization of microsoft/Phi-3.5-mini-instruct (© Microsoft, MIT), used by the CodeRoast Sift --explain local-narrative feature.

Modification (MIT): quantized to GGUF Q4_K_M (no importance matrix) by CodeRoast from microsoft/Phi-3.5-mini-instruct @ 2fe192450127e6a83f7441aef6e3ca586c338b77 using llama.cpp b9672. Reproducible: insight-eidos/scripts/quantize_phi35.sh.

File: phi-3.5-mini-instruct-Q4_K_M.gguf
SHA-256: c5347cbd620330a7c051c3d2fcad156b2c606340682f3d09c92df5bcfb9deaba
License: MIT (the upstream LICENSE + NOTICE.md are included in this repo, unmodified).

Downloads last month: 22

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CodeRoasted/tamys-explain-model

Base model

microsoft/Phi-3.5-mini-instruct

Quantized

(204)

this model