Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mlabonne/gemma-3-12b-it-abliterated
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: gemma
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
tags:
|
| 7 |
+
- llama-cpp
|
| 8 |
+
- matrixportal
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# matrixportal/gemma-3-12b-it-abliterated-GGUF
|
| 12 |
+
This model was converted to GGUF format from [`mlabonne/gemma-3-12b-it-abliterated`](https://huggingface.co/mlabonne/gemma-3-12b-it-abliterated) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
|
| 13 |
+
Refer to the [original model card](https://huggingface.co/mlabonne/gemma-3-12b-it-abliterated) for more details on the model.
|
| 14 |
+
|
| 15 |
+
## ✅ Quantized Models Download List
|
| 16 |
+
|
| 17 |
+
### 🔍 Recommended Quantizations
|
| 18 |
+
- **✨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q4_k_m.gguf) (Best balance of speed/quality)
|
| 19 |
+
- **📱 ARM Devices:** [`Q4_0`](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q4_0.gguf) (Optimized for ARM CPUs)
|
| 20 |
+
- **🏆 Maximum Quality:** [`Q8_0`](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q8_0.gguf) (Near-original quality)
|
| 21 |
+
|
| 22 |
+
### 📦 Full Quantization Options
|
| 23 |
+
| 🚀 Download | 🔢 Type | 📝 Notes |
|
| 24 |
+
|:---------|:-----|:------|
|
| 25 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q2_k.gguf) |  | Basic quantization |
|
| 26 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q3_k_s.gguf) |  | Small size |
|
| 27 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q3_k_m.gguf) |  | Balanced quality |
|
| 28 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q3_k_l.gguf) |  | Better quality |
|
| 29 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q4_0.gguf) |  | Fast on ARM |
|
| 30 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q4_k_s.gguf) |  | Fast, recommended |
|
| 31 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q4_k_m.gguf) |  ⭐ | Best balance |
|
| 32 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q5_0.gguf) |  | Good quality |
|
| 33 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q5_k_s.gguf) |  | Balanced |
|
| 34 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q5_k_m.gguf) |  | High quality |
|
| 35 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q6_k.gguf) |  🏆 | Very good quality |
|
| 36 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-q8_0.gguf) |  ⚡ | Fast, best quality |
|
| 37 |
+
| [Download](https://huggingface.co/matrixportal/gemma-3-12b-it-abliterated-GGUF/resolve/main/gemma-3-12b-it-abliterated-f16.gguf) |  | Maximum accuracy |
|
| 38 |
+
|
| 39 |
+
💡 **Tip:** Use `F16` for maximum precision when quality is critical
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
---
|
| 43 |
+
# 🚀 Applications and Tools for Locally Quantized LLMs
|
| 44 |
+
## 🖥️ Desktop Applications
|
| 45 |
+
|
| 46 |
+
| Application | Description | Download Link |
|
| 47 |
+
|-----------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 48 |
+
| **Llama.cpp** | A fast and efficient inference engine for GGUF models. | [GitHub Repository](https://github.com/ggml-org/llama.cpp) |
|
| 49 |
+
| **Ollama** | A streamlined solution for running LLMs locally. | [Website](https://ollama.com/) |
|
| 50 |
+
| **AnythingLLM** | An AI-powered knowledge management tool. | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm) |
|
| 51 |
+
| **Open WebUI** | A user-friendly web interface for running local LLMs. | [GitHub Repository](https://github.com/open-webui/open-webui) |
|
| 52 |
+
| **GPT4All** | A user-friendly desktop application supporting various LLMs, compatible with GGUF models. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 53 |
+
| **LM Studio** | A desktop application designed to run and manage local LLMs, supporting GGUF format. | [Website](https://lmstudio.ai/) |
|
| 54 |
+
| **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 55 |
+
|
| 56 |
+
---
|
| 57 |
+
|
| 58 |
+
## 📱 Mobile Applications
|
| 59 |
+
|
| 60 |
+
| Application | Description | Download Link |
|
| 61 |
+
|-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 62 |
+
| **ChatterUI** | A simple and lightweight LLM app for mobile devices. | [GitHub Repository](https://github.com/Vali-98/ChatterUI) |
|
| 63 |
+
| **Maid** | Mobile Artificial Intelligence Distribution for running AI models on mobile devices. | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid) |
|
| 64 |
+
| **PocketPal AI** | A mobile AI assistant powered by local models. | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai) |
|
| 65 |
+
| **Layla** | A flexible platform for running various AI models on mobile devices. | [Website](https://www.layla-network.ai/) |
|
| 66 |
+
|
| 67 |
+
---
|
| 68 |
+
|
| 69 |
+
## 🎨 Image Generation Applications
|
| 70 |
+
|
| 71 |
+
| Application | Description | Download Link |
|
| 72 |
+
|-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 73 |
+
| **Stable Diffusion** | An open-source AI model for generating images from text. | [GitHub Repository](https://github.com/CompVis/stable-diffusion) |
|
| 74 |
+
| **Stable Diffusion WebUI** | A web application providing access to Stable Diffusion models via a browser interface. | [GitHub Repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui) |
|
| 75 |
+
| **Local Dream** | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference. | [GitHub Repository](https://github.com/xororz/local-dream) |
|
| 76 |
+
| **Stable-Diffusion-Android (SDAI)** | An open-source AI art application for Android devices, enabling digital art creation. | [GitHub Repository](https://github.com/ShiftHackZ/Stable-Diffusion-Android) |
|
| 77 |
+
|
| 78 |
+
---
|
| 79 |
+
|