ibm-graniteのgranite-4.0-micro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
52
GGUF
Model size
3B params
Architecture
granitehybrid
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

16-bit

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

Model tree for tatsuyaaaaaaa/granite-4.0-micro-gguf

Quantized
(24)
this model

Dataset used to train tatsuyaaaaaaa/granite-4.0-micro-gguf

Collection including tatsuyaaaaaaa/granite-4.0-micro-gguf