PocketWeights/Gemma-4-12B-agentic-abliterated-GGUF overview
⚡ PocketWeights: Gemma 4 12B agentic abliterated GGUF Heavy models, made light. We specialize in high quality GGUF quantizations optimized for edge devices and…
Runs locally from ~5.34 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | PocketWeights/Gemma-4-12B-agentic-abliterated-GGUF |
|---|---|
| Author | PocketWeights |
| Pipeline | — |
| License | gemma |
| Base model | huihui-ai/Huihui-gemma-4-12B-agentic-fable5-abliterated |
| Last modified | 2026-08-03T16:16:04.000Z |
Model README
---
base_model: huihui-ai/Huihui-gemma-4-12B-agentic-fable5-abliterated
library_name: gguf
license: gemma
tags:
- gguf
- quantized
- abliterated
---
⚡ PocketWeights: Gemma-4-12B-agentic-abliterated-GGUF
Heavy models, made light. We specialize in high-quality GGUF quantizations optimized for edge devices and gaming laptops.
What is this model?
This is an optimized GGUF of huihui-ai/Huihui-gemma-4-12B-agentic-fable5-abliterated. It is designed to provide massive reasoning capabilities while fitting perfectly into consumer hardware.
📦 Pick Your Hardware
We bypass the confusing wall of files to provide specific sizes optimized for your hardware:
IQ3_M(Fits hardware constraint): For older laptops (GTX 1650, RTX 3050).Q4_K_M(Fits hardware constraint): The standard. Perfect for RTX 3060/4050.
🚀 Quick Start Guide
Option 1: LM Studio (Easiest)
- Download & open LM Studio.
- In the search bar, type:
PocketWeights/Gemma-4-12B-agentic-abliterated-GGUF. - Select your hardware size, click Download, and hit Play!
Option 2: Ollama
If you have Ollama installed, simply run this command in your terminal:
ollama run hf.co/PocketWeights/Gemma-4-12B-agentic-abliterated-GGUF:Q4_K_MRun PocketWeights/Gemma-4-12B-agentic-abliterated-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models