Downloads · 30 days
38
5% of all-time downloads
TaterTotterson/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx-Tater-NoThink
Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx-Tater-NoThink is a text generation model from TaterTotterson. Use it when you need the model to write or continue text. It is set up for mlx-node. The card lists the license as gemma.
This is a Tater NoThink repack of Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4KXL-mlx.
Downloads · 30 days
38
5% of all-time downloads
All-time downloads
725
Public
Parameters
25.8B
34.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.3 GB · 100%
How the weights are stored.
U3224.8B · 96%
From the Hugging Face model README
This is a Tater NoThink repack of Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx.
chat_template.jinja now forces enable_thinking = false.Tater works best with models that answer directly and do not emit hidden reasoning or thinking blocks. This repo keeps the same MLX quantized model but makes the default chat template run in NoThink mode for runtimes that use the embedded template.
This model inherits the Gemma Terms of Use from the base model.