Files

ModelHub XC d9d3041c89 初始化项目，由ModelHub XC社区提供模型

Model: Swicked86/phi4-mm-gguf
Source: Original Platform

2026-10-25 21:24:21 +08:00

3.8 KiB

Raw Permalink Blame History

license, base_model, tags, language, pipeline_tag

license

base_model

Phi-4 Multimodal Instruct — GGUF Quantizations

CPU-optimised GGUF quantizations of microsoft/Phi-4-multimodal-instruct produced with llama.cpp.

Model Summary

Phi-4-multimodal-instruct is a 5.6 B parameter lightweight multimodal foundation model by Microsoft that processes text, image, and audio inputs. The backbone LLM is Phi-4-Mini (3.8 B). This repository contains GGUF quantizations for local CPU and GPU deployment.

Context length: 128 K tokens (131 072)
Architecture: phi3 (GGUF)
License: MIT — © Microsoft Corporation

Available Files

File	Quant	Size	BPW	Best for
`phi4-mm-Q4_K_M.gguf`	Q4_K_M	2.37 GB	5.18	CPU inference, 8 GB RAM systems
`phi4-mm-Q8_0.gguf`	Q8_0	3.90 GB	8.00	GPU/high-RAM systems, near-lossless
`phi4-mm-f16.gguf`	F16	7.17 GB	16.00	Source / re-quantization base

Quantization Method

Quantized using llama-quantize from ggerganov/llama.cpp (build 8334).

llama-quantize phi4-mm-f16.gguf phi4-mm-Q4_K_M.gguf Q4_K_M 16

Source weights converted from the original safetensors using convert_hf_to_gguf.py.

Recommended Usage

Ollama (CPU — Intel NUC / low-power hardware)

# Pull and run (once uploaded to Ollama registry)
ollama run phi4-mm-nuc

# Or import from GGUF directly with a Modelfile:
ollama create phi4-mm-nuc -f Modelfile
ollama run phi4-mm-nuc

Modelfile for 8 GB RAM / no GPU:

FROM phi4-mm-Q4_K_M.gguf
PARAMETER num_ctx 8192
PARAMETER num_thread 8
PARAMETER num_gpu 0
PARAMETER flash_attn false
PARAMETER temperature 0.7
PARAMETER repeat_penalty 1.1
SYSTEM "You are a helpful, accurate, and concise AI assistant."

llama.cpp CLI (GPU, full quality)

./build/bin/llama-cli \
  -m phi4-mm-Q8_0.gguf \
  --ctx-size 65536 \
  --flash-attn on \
  --kv-offload \
  -ngl 99 \
  --threads 16

OpenClaw Integration

In ~/.openclaw/openclaw.json:

{
  "agent": {
    "model": "ollama/phi4-mm-nuc"
  },
  "modelConfigs": {
    "ollama/phi4-mm-nuc": {
      "provider": "ollama",
      "model": "phi4-mm-nuc",
      "baseUrl": "http://localhost:11434"
    }
  }
}

Hardware Notes

Hardware	Recommended quant	Context	Notes
Intel NUC 11th Gen, 8 GB RAM	Q4_K_M	8 192	CPU-only, `num_gpu 0`
Laptop / desktop, 16 GB RAM	Q5_K_M or Q8_0	16 384	CPU or iGPU
GPU with ≥ 8 GB VRAM	Q8_0 or F16	32 768–65 536	Full `-ngl 99` offload

License

This repository redistributes quantized weights derived from microsoft/Phi-4-multimodal-instruct under the original MIT License.

MIT License
Copyright (c) Microsoft Corporation.

Quantization tooling (llama.cpp) is also MIT licensed. See llama.cpp LICENSE.

Attribution

Original model: Microsoft Research
Quantization: produced with llama.cpp by Georgi Gerganov et al.
Technical report: arXiv:2503.01743

3.8 KiB Raw Permalink Blame History Unescape Escape