TaterTotterson/gemma-4-12b-it-GGUF-Tater-NoThink overview
Gemma 4 12B IT GGUF Tater NoThink This is a Tater NoThink repack of unsloth/gemma 4 12b it GGUF using the UD Q4 K XL GGUF and the matching mmproj F16.gguf proj…
Runs locally from ~167.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | TaterTotterson/gemma-4-12b-it-GGUF-Tater-NoThink |
|---|---|
| Author | TaterTotterson |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | unsloth/gemma-4-12b-it-GGUF |
| Last modified | 2026-06-06T22:26:34.000Z |
Model README
---
license: apache-2.0
library_name: llama.cpp
pipeline_tag: image-text-to-text
tags:
- tater-pick
- tater-recommended
- tater-nothink
- nothink
- thinking-disabled
- llama.cpp
- gguf
- gemma4
- vision
- UD-Q4_K_XL
base_model:
- unsloth/gemma-4-12b-it-GGUF
---
Gemma 4 12B IT GGUF - Tater NoThink
This is a Tater NoThink repack of unsloth/gemma-4-12b-it-GGUF using the UD-Q4_K_XL GGUF and the matching mmproj-F16.gguf projector.
The embedded GGUF chat template has been patched to set:
{%- set enable_thinking = false -%}No weights were changed.
Files
gemma-4-12b-it-UD-Q4_K_XL.ggufmmproj-F16.gguf
Tater
This repo is tagged as a Tater Pick so it can appear in Tater's Hugging Face browser. It is intended for local llama.cpp text and vision use with thinking disabled by default.
Source
Original model repo: https://huggingface.co/unsloth/gemma-4-12b-it-GGUF
Run TaterTotterson/gemma-4-12b-it-GGUF-Tater-NoThink with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models