Model catalog

Phi-4 Mini Instruct

Microsoft's 3.8B instruction model provides a compact alternative with a publisher-documented 128K context limit.

Check this model on your hardware See what your PC can run

Model overview

Family: Phi-4
Provider: Microsoft
Architecture: Phi
Parameters: 3.8B
Formats: gguf, safetensors
Runtimes: llama.cpp
License: MIT
Maximum context: 131,072 tokens

Available quantizations

Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.

Q4_K_M

A commonly available lower-memory GGUF variant; the listed memory input is an estimate, not the repository file size.

Bits per weight: 4.5
Source: second-state/Phi-4-mini-instruct-GGUF GGUF repository

Q8_0

A higher-memory GGUF variant where listed by the conversion repository; the listed memory input remains approximate.

Bits per weight: 8
Source: second-state/Phi-4-mini-instruct-GGUF GGUF repository

Compatibility notes

Weight estimates are approximate and include a runtime overhead. Real requirements vary with context length, runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.

Microsoft Phi-4 Mini Instruct model card; verified value, last verified 2026-09-23. Microsoft reports 3.8B parameters, 128K context, and MIT licensing. GGUF is a community conversion; runtime-specific context memory is not estimated. View source