tatsuyaaaaaaa
/

gemma-3-4b-it-gguf

Model card Files Files and versions Community

Googleのgemma-3-4b-it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: 166

GGUF

Model size

3.88B params

Architecture

gemma3

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/gemma-3-4b-it-gguf

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(96)

this model

Dataset used to train tatsuyaaaaaaa/gemma-3-4b-it-gguf

Collection including tatsuyaaaaaaa/gemma-3-4b-it-gguf

gemma3

googleのgemma3に関連するコレクション • 3 items • Updated 2 days ago