MicrosoftのPhi-4-mini-reasoningをgguf変換したものです。

imatrix量子化時にはTFMC/imatrix-dataset-for-japanese-llmのデータセットを用いています。

Downloads last month
89
GGUF
Model size
3.84B params
Architecture
phi3
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tatsuyaaaaaaa/Phi-4-mini-reasoning-gguf

Quantized
(28)
this model

Dataset used to train tatsuyaaaaaaa/Phi-4-mini-reasoning-gguf

Collection including tatsuyaaaaaaa/Phi-4-mini-reasoning-gguf