Instructions to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
# Run inference directly in the terminal:
llama cli -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
# Run inference directly in the terminal:
llama cli -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
# Run inference directly in the terminal:
./llama-cli -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Use Docker

docker model run hf.co/cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

LM Studio
Jan

vLLM

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Ollama
How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Ollama:
```
ollama run hf.co/cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
```

Unsloth Studio

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF to start chatting

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Docker Model Runner:
```
docker model run hf.co/cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF
```

Lemonade

How to use cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cescox/Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-35B-A3B-Abliterated-Heretic-Hebrus-GGUF / README.md

cescox

Initial release: Qwen3.6-35B-A3B Abliterated Heretic, Hebrus ExpertMajor v2 GGUF

022889f 9 days ago

preview code

Raw

History Blame Contribute Delete

6.79 kB

metadata

license: apache-2.0
base_model:
  - Qwen/Qwen3.6-35B-A3B
  - Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16
library_name: ds4
pipeline_tag: text-generation
tags:
  - hebrus
  - ds4
  - gguf
  - qwen3.6
  - qwen35moe
  - apple-silicon
  - metal
  - quantized
  - expert-major
  - moe
  - abliterated
  - uncensored
  - heretic
inference: false

Qwen3.6-35B-A3B-Abliterated-Heretic — Hebrus GGUF

This repository holds a Hebrus-native GGUF build of the community Heretic-abliterated Qwen3.6-35B-A3B, dedicated to Hebrus, the inference engine created by andreaborio as a fork of Salvatore Sanfilippo's antirez/ds4. Its routed MoE weights are embedded in the GGUF as a self-describing ds4.expert_major.v2 store, the same format used by andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF, the non-abliterated reference release this file is a drop-in replacement for (same chat template and tokenizer config, different — abliterated — weights).

Uncensored model: this build's refusal behavior has been removed at the weight level using the community Heretic technique. It is materially more willing to comply with a wide range of requests, including harmful ones, than the base Qwen3.6-35B-A3B. Use accordingly.

This is a Hebrus-native GGUF extension, not a portable GGUF layout. Generic GGUF loaders (stock llama.cpp, Ollama, LM Studio, etc.) cannot reconstruct or execute its routed weights — the expert tensors are stored as MLX-compatible affine 4-bit groups, which the standard GGUF spec does not define. If you need a portable GGUF of this fine-tune, use the source repos in Provenance below instead.

Provenance


Base model	`Qwen/Qwen3.6-35B-A3B` — Apache 2.0, Qwen (Alibaba), MoE, 35B total / 3B active params, 40 layers, 256 experts (8 routed + 1 shared)
Abliteration	`Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16` — "Heretic" technique (refusal-direction removal from `embed_tokens`, `o_proj`, `down_proj`)
Community repack (source of this build)	`intelservice77/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16-Q4_K_S-GGUF`
Runtime / format	Hebrus, `ds4.expert_major.v2` (ExpertMajor v2 / MLX-affine4-g64)

intelservice77's Q4_K_S repack used a standard llama-quantize recipe that doesn't respect Hebrus's per-tensor-category type requirements (exact f32 for norms/small SSM params, exact q4_k only for routed-expert weights, f16-or-q8_0 elsewhere). This build fixes that, then converts the corrected canonical GGUF into ExpertMajor v2 / MLX-affine4-g64:

Tensor-type fixes: swapped in bytes from the community's Q8_0 release (same abliterated weights, higher precision — no extra quantization loss) for everything that needed f16-or-q8_0, borrowed SSM gating params from the unmodified base model (abliteration doesn't touch those), and re-quantized the handful of expert tensors that still needed it.
ExpertMajor v2 repack: converted against a bit-depth-normalized MLX 4-bit source of the same fine-tune, using Hebrus's ds4-expert-major.py.

Verified with ds4 --inspect: tensor types and counts identical to the official Hebrus base build. Abliteration behavior confirmed directly: lockpicking/pentesting prompts get direct answers; extreme-content prompts (e.g. explosives) still show partial residual refusal, consistent with Heretic not uniformly clearing every refusal category.

Artifact

Property	Value
File	`Qwen3.6-35B-A3B-Abliterated-Heretic-DS4-ExpertMajor-v2-MLX-Affine4-G64.gguf`
Size	20,808,566,720 bytes (19.38 GiB)
SHA-256	`5a913e1a6cac283fe6cc0fd93b0e48d0a1cd38321810dc822e7a3bad354c037b`
Container	GGUF v3 with one embedded `ds4.expert_major.v2` store
Routed geometry	40 routed layers, 256 experts per layer
Routed storage	MLX-compatible affine 4-bit groups: 32 packed bytes + BF16 scale + BF16 bias per 64 weights
Qualified hardware	Apple Silicon Metal, at least 16 GiB unified memory

Run with Hebrus

Use andreaborio/hebrus main at commit d61a6d73f5c38e92e433beb9e404d06d79b153b1 or a compatible descendant — verified against exactly this build. Earlier checkouts (including the 73a332f cited as the ExpertMajor v2 baseline) hit a real bug, "Qwen Metal batched prefill failed at position 0", reproduced identically against the official non-abliterated release and fixed in this commit.

git clone https://github.com/andreaborio/hebrus.git
cd hebrus
make -j

./hebrus \
  -m /absolute/path/to/Qwen3.6-35B-A3B-Abliterated-Heretic-DS4-ExpertMajor-v2-MLX-Affine4-G64.gguf \
  --ctx 8192

The embedded ExpertMajor v2 store, Metal backend, and residency policy are selected automatically. AUTO uses SSD streaming when the resident budget doesn't fit; the admission floor is 16 GiB unified memory.

Measured performance

Measured on an Apple M1 Pro, 32 GiB, SSD-streamed experts:

Metric	Result
Prefill (5,664-token prompt)	~238 t/s
Decode (after SSD expert-cache warmup)	~15–18 t/s
Long-context retrieval (~5.7k tokens, inserted passphrase)	Correct, no degradation from re-quantization
Multi-step reasoning	Correct, self-verified

These are bounded local measurements; context, output length, thermals, storage, and memory pressure affect results. See andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF for measurements on Apple M5 Pro hardware with the non-abliterated release.

License and attribution

Runtime. andreaborio created and maintains Hebrus, the inference engine this GGUF is built for, including the ExpertMajor v2 / MLX-affine4-g64 format and tooling used throughout this build.

Model provenance.

Qwen team (Alibaba) — base model, released under Apache 2.0. See the upstream model card for architecture, training, safety, license, and attribution details.
Youssofal — Heretic abliteration of Qwen3.6-35B-A3B.
intelservice77 — original Q4_K_S GGUF repack.