Brunobkr/OFFFELLIA_f16_huihui-ai_MTP-Qwen3.8-27B-abliterated.gguf overview
<p align="center" <img src="capa.png" alt="ΩFFΣLLIα llama.cpp Helicoidal Quantization" width="100%" style="border radius: 12px; box shadow: 0 10px 30px rgba 16…
Runs locally from ~50.90 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| OFFFELLIA_f16_huihui-ai_MTP-Qwen3.8-27B-abliterated.gguf | GGUF | F16 | 50.90 GB | Download |
Model Details
| Model ID | Brunobkr/OFFFELLIA_f16_huihui-ai_MTP-Qwen3.8-27B-abliterated.gguf |
|---|---|
| Author | Brunobkr |
| Pipeline | text-generation |
| License | mit |
| Base model | — |
| Last modified | 2026-08-16T20:47:05.000Z |
Model README
---
license: mit
language:
- pt
- en
library_name: gguf
pipeline_tag: text-generation
tags:
- llama.cpp
- gguf
- quantization
- offerlia
- helicoidal-sieve
- ggml
- cplusplus
pretty_name: ΩFFΣLLIα — llama.cpp Helicoidal Quantization
---
<p align="center">
<img src="capa.png" alt="ΩFFΣLLIα llama.cpp Helicoidal Quantization" width="100%" style="border-radius: 12px; box-shadow: 0 10px 30px rgba(168, 85, 247, 0.2);" />
</p>
<h1 align="center">ΩFFΣLLIα — llama.cpp Helicoidal Quantization </h1>
<p align="center">
<strong>Fork de alta performance do llama.cpp ZETAHELICOIDAL ( quants.py )</strong>
</p>
<p align="center">
<a href="#-visão-geral"><img src="https://img.shields.io/badge/GGUF-v3%20Native-purple?style=for-the-badge" alt="GGUF Native"></a>
<a href="#-tabela-de-arquivos-modificados"><img src="https://img.shields.io/badge/GGML-Quant%20Q4__2__H-fuchsia?style=for-the-badge" alt="Quant Q4_2_H"></a>
<a href="#-como-compilar-e-usar"><img src="https://img.shields.io/badge/C%2B%2B-17%20Build-blueviolet?style=for-the-badge" alt="C++ Build"></a>
<a href="https://huggingface.co"><img src="https://img.shields.io/badge/Hugging%20Face-Compatible-orange?style=for-the-badge" alt="HuggingFace Ready"></a>
</p>
---
📌 Visão Geral
O ΩFFΣLLIα é um fork otimizado do ecossistema llama.cpp / GGML, projetado para integrar avanços da Teoria Aritmético-Harmônica de Becker ao pipeline de inferência de Modelos de Linguagem de Grande Porte (LLMs).
---
🚀 Como Compilar e Usar
1. Compilar o llama.cpp Otimizado
cd llama.cpp
mkdir -p build && cd build
cmake .. -DLLAMA_BUILD_EXAMPLES=ON
cmake --build . --config Release -j$(nproc)
2. Converter Modelo Hugging Face para GGUF Q4_2_H
python3 llama.cpp/convert_hf_to_gguf.py path/to/hf-model \
--outtype q4_2_h \
--outfile models/modelo-q4_2_h.gguf
3. Quantizar Modelo F16/F32 Existente
./llama.cpp/build/bin/llama-quantize ./models/modelo-f16.gguf ./models/modelo-q4_2_h.gguf Q4_2_H
4. Executar Inferência via CLI
./llama.cpp/build/bin/llama-cli -m ./models/modelo-q4_2_h.gguf -p "ΩFFΣLLIα: Explique a Teoria Helicoidal" -n 256
5. Executar a Aplicação Web & Dashboard
npm run build
npm start
---
<p align="center">
Desenvolvido para alta eficiência em execução local e integração com o ecossistema Hugging Face.
</p>
Run Brunobkr/OFFFELLIA_f16_huihui-ai_MTP-Qwen3.8-27B-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