GGUF
English
Japanese
imatrix
conversational

phi-4-gguf

microsoftใ•ใ‚“ใŒๅ…ฌ้–‹ใ—ใฆใ„ใ‚‹phi-4ใฎggufใƒ•ใ‚ฉใƒผใƒžใƒƒใƒˆๅค‰ๆ›็‰ˆใงใ™ใ€‚

imatrixใฎใƒ‡ใƒผใ‚ฟใฏTFMC/imatrix-dataset-for-japanese-llmใ‚’ไฝฟ็”จใ—ใฆไฝœๆˆใ—ใพใ—ใŸใ€‚

Usage

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
build/bin/llama-cli -m 'phi-4-Q4_0.gguf' -n 128 -c 128 -p 'ใ‚ใชใŸใฏใƒ—ใƒญใฎๆ–™็†ไบบใงใ™ใ€‚ใƒฌใ‚ทใƒ”ใ‚’ๆ•™ใˆใฆ' -cnv
Downloads last month
787
GGUF
Model size
15B params
Architecture
phi3
Hardware compatibility
Log In to add your hardware

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mmnga/phi-4-gguf

Base model

microsoft/phi-4
Quantized
(169)
this model

Dataset used to train mmnga/phi-4-gguf