Model Intelligence Sheet
1bit-MONSTER/phi-4-GGUF overview
phi 4 — GGUF Q4 K M Microsoft's own Q4 K M GGUF, re hosted with measured performance for the 1bit engine https://github.com/1bit MONSTER/engine on Strix Halo. …
Runs locally from ~8.43 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| phi-4-Q4_K.gguf | GGUF | Q4_K | 8.43 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/phi-4-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | mit |
| Base model | microsoft/phi-4 |
| Last modified | 2026-09-26T15:21:16.000Z |
Model README
---
license: mit
base_model:
- microsoft/phi-4
tags:
- gguf
---
phi-4 — GGUF (Q4_K_M)
Microsoft's own Q4_K_M GGUF, re-hosted with measured performance for the
1bit engine on Strix Halo.
Contents
phi-4-Q4_K.gguf(Q4_K_M)
Measured performance (Strix Halo, Vulkan)
pp512: 543 tok/s · tg128: 19.4 tok/s
Running it
1bit serve -m phi-4-Q4_K.gguf --device vulkanAttribution
- Model and quantization: microsoft/phi-4-gguf, MIT.
- License: MIT, inherited from the base model.
Run 1bit-MONSTER/phi-4-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models