GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

mparvin/phi-2-GGUF overview

phi 2 GGUF GGUF conversions of microsoft/phi 2 https://huggingface.co/microsoft/phi 2 . These weights were converted with llama.cpp https://github.com/ggergano…

ggufquantizedllama.cppbase_model:microsoft/phi-2base_model:quantized:microsoft/phi-2endpoints_compatibleregion:us

Runs locally from ~1.62 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
phi-2-q4_k_m.ggufGGUFQ4_K_M1.62 GBDownload
phi-2-q5_k_m.ggufGGUFQ5_K_M1.87 GBDownload
phi-2-q8_0.ggufGGUFQ8_02.75 GBDownload

Model Details

Model IDmparvin/phi-2-GGUF
Authormparvin
Pipeline
License
Base modelmicrosoft/phi-2
Last modified2026-09-01T04:48:34.000Z

Model README

---

base_model: microsoft/phi-2

tags:

  • gguf
  • quantized
  • llama.cpp

---

phi-2-GGUF

GGUF conversions of microsoft/phi-2.

These weights were converted with llama.cpp and quantized for local / Ollama use. This is not the original model; it is a community conversion of the source weights.

Quantizations

Q4_K_M, Q5_K_M, Q8_0

Source

Run mparvin/phi-2-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models