Modelpublic

second-state/Phi-4-mini-instruct-GGUF

sourceHugging Facemitupdated 1y agoView on Hugging Face

2likes854downloads

Model Card

<div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">

Phi-4-mini-instruct-GGUF

Original Model

microsoft/Phi-4-mini-instruct

Run with LlamaEdge

—LlamaEdge version: v0.16.9 and above

—Prompt template

—Prompt type: phi-4-chat

—Prompt string

text

    <|im_start|>system<|im_sep|>
    {system_message}<|im_end|>
    <|im_start|>user<|im_sep|>
    {user_message}<|im_end|>
    <|im_start|>assistant<|im_sep|>

—Context size: 128000

—Run as LlamaEdge service

bash

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-instruct-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template phi-4-chat \
    --ctx-size 128000 \
    --model-name phi-4-mini

—Run as LlamaEdge command app

bash

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-instruct-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template phi-4-chat \
    --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Phi-4-mini-instruct-Q2_K.gguf	Q2_K	2	1.68 GB	smallest, significant quality loss - not recommended for most purposes
Phi-4-mini-instruct-Q3_K_L.gguf	Q3KL	3	2.25 GB	small, substantial quality loss
Phi-4-mini-instruct-Q3_K_M.gguf	Q3KM	3	2.12 GB	very small, high quality loss
Phi-4-mini-instruct-Q3_K_S.gguf	Q3KS	3	1.90 GB	very small, high quality loss
Phi-4-mini-instruct-Q4_0.gguf	Q4_0	4	2.33 GB	legacy; small, very high quality loss - prefer using Q3KM
Phi-4-mini-instruct-Q4_K_M.gguf	Q4KM	4	2.49 GB	medium, balanced quality - recommended
Phi-4-mini-instruct-Q4_K_S.gguf	Q4KS	4	2.34 GB	small, greater quality loss
Phi-4-mini-instruct-Q5_0.gguf	Q5_0	5	2.73 GB	legacy; medium, balanced quality - prefer using Q4KM
Phi-4-mini-instruct-Q5_K_M.gguf	Q5KM	5	2.85 GB	large, very low quality loss - recommended
Phi-4-mini-instruct-Q5_K_S.gguf	Q5KS	5	2.73 GB	large, low quality loss - recommended
Phi-4-mini-instruct-Q6_K.gguf	Q6_K	6	3.16 GB	very large, extremely low quality loss
Phi-4-mini-instruct-Q8_0.gguf	Q8_0	8	4.08 GB	very large, extremely low quality loss - not recommended
Phi-4-mini-instruct-f16.gguf	f16	16	7.68 GB

Quantized with llama.cpp b4792.