← back to catalog · registered 2026-10-06 00:58

Brunobkr/OFFFELLIA_Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored.gguf

Brunobkr 30B MoE
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Brunobkr%2FOFFFELLIA_Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored.gguf"
Response includes
  • classification m3
  • files 4
  • author_summary 44 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-10-06

Metadata

Tags
gguf doi:10.57967/hf/10788 region:us

Related

Total size
0 B
Files
4
Quantizations
1
Registered
2026-10-06 00:58
Last updated on HF
2026-10-06 02:42

Files by quantization

Auxiliary files 4 files 2.84 MB
capa.png 2.14 MB 34b0b662 download
pix.jpeg 711 KB a41f92d9 download
README.md 3.84 KB ba3332fc download
.gitattributes 1.57 KB 2e1cf7a5 download

README current version from Hugging Face

ΩFFFΣLLIa • llama.cpp • OFFFELLIA_HERETIC

OFFFELLIA_HERETIC Banner

OFFFELLIA_HERETIC Web UI -

   ██████╗ ███████╗███████╗███████╗██╗     ██╗     ██╗ █████╗ 
  ██╔═══██╗██╔════╝██╔════╝██╔════╝██║     ██║     ██║██╔══██╗
  ██║   ██║█████╗  █████╗  █████╗  ██║     ██║     ██║███████║
  ██║   ██║██╔══╝  ██╔══╝  ██╔══╝  ██║     ██║     ██║██╔══██║
  ╚██████╔╝██║     ██║     ███████╗███████╗███████╗██║██║  ██║-HERETIC
   ╚═════╝ ╚═╝     ╚═╝     ╚══════╝╚══════╝╚══════╝╚═╝╚═╝  ╚═╝

High-Performance LLM / VLM Inference & Autonomous Agentic Ecosystem in Pure C/C++

License: MIT
C++: 17/20
WebUI: SvelteKit + Vite
Status: Unlocked & Optimized
Agentic: Multi--Turn Engine


📖 Visão Geral

ΩFFFΣLLIa • llama.cpp • AlgMor24 é um fork avançado, destravado e de alta performance do ecossistema llama.cpp. Este projeto integra inferência local de última geração em C/C++ com um motor agêntico autônomo multi-turn, suporte nativo a FIM (Fill-in-the-Middle) para geração e preenchimento de código, Speculative Decoding otimizado para programação, integração de ferramentas MCP (Model Context Protocol) e uma interface Web moderna em SvelteKit/Vite com a identidade visual Cyberpunk Neon Fire.


✨

git clone https://github.com/brunoconta1980-tech/llama_OFFFELLIA_1984

TKS TO: https://huggingface.co/mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-BF16/tree/main

cd llama_OFFFELLIA_1984

cmake -B build
-DGGML_VULKAN=ON
-DLLAMA_BUILD_WEBUI=ON
-DLLAMA_SERVER_TOOLS=ON

cmake --build build -j

or

cmake -S . -B build-vulkan
-DGGML_VULKAN=ON
-DLLAMA_BUILD_WEBUI=ON
-DLLAMA_SERVER_TOOLS=ON

cmake --build build-vulkan -j

Comando sugerido:

"/home/userk21/OFFFELLIA_llama.cpp_Neon_Themes/build/bin/llama-server"
-m "/home/userk21/Área de trabalho/userk21/LLMS/ΩFFFΣLLIα_Q5_K_coder3101_gemma-4-E4B-8b_666-tensors-heretic.gguf"
-ngl 99 --n-cpu-moe 99
-c 50000
-t 5
-tb 5
-ctk q8_0
-ctv q8_0
-fa on
--cpu-strict 1
--parallel 1
--agent
--tools all
--reasoning auto
--kv-unified
--load-mode mmap
--cors-origins "*"
--webui-mcp-proxy
--threads-http -1
--port 8080
--host 127.0.0.1


📜 Licença

Distribuído sob a licença MIT. Veja o arquivo LICENSE para mais detalhes.
Gracias https://github.com/charlie12345/ROCmFPX


ΩFFFΣLLIa • llama.cpp • AlgMor24 — Inferência Local, Descentralizada e Sem Limites
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration