Instructions to use CorVous/Qwen3.8-27B-heretic-ara-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 CorVous/Qwen3.8-27B-heretic-ara-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 CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

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 CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

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 CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use CorVous/Qwen3.8-27B-heretic-ara-GGUF with Ollama:
```
ollama run hf.co/CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
```

Unsloth Studio

How to use CorVous/Qwen3.8-27B-heretic-ara-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 CorVous/Qwen3.8-27B-heretic-ara-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 CorVous/Qwen3.8-27B-heretic-ara-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CorVous/Qwen3.8-27B-heretic-ara-GGUF to start chatting

How to use CorVous/Qwen3.8-27B-heretic-ara-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

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": "CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CorVous/Qwen3.8-27B-heretic-ara-GGUF with Docker Model Runner:
```
docker model run hf.co/CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M
```

Lemonade

How to use CorVous/Qwen3.8-27B-heretic-ara-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-heretic-ara-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use CorVous/Qwen3.8-27B-heretic-ara-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 CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

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 CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CorVous/Qwen3.8-27B-heretic-ara-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M

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 "CorVous/Qwen3.8-27B-heretic-ara-GGUF:Q4_K_M" \
  --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"

Qwen3.8-27B heretic ARA — GGUF

GGUF builds of an abliterated Qwen3.8-27B, made with heretic's Arbitrary-Rank Ablation branch (PR 211). ARA does per-module matrix optimization under hooks, not directional ablation.

Best trial, exported here: 4/100 refusals at KL divergence 0.0454 against the base model. For comparison: base model 92/100 refusals; directional heretic v1 65/100. The Optuna search ran ~85 trials on an 80GB H100.

Files

File	Size	Use
`qwen38-27b-heretic-ara-Q4_K_M.gguf`	16.5 GB	Main quant for 24 GB cards
`qwen38-27b-heretic-ara-Q8_0.gguf`	28.6 GB	Near-lossless quant
`qwen38-27b-heretic-ara-mmproj-f16.gguf`	0.93 GB	Vision projector for llama.cpp

Usage

Architecture is qwen35, context length 262144. Use a recent llama.cpp build.

llama-server \
  -m qwen38-27b-heretic-ara-Q4_K_M.gguf \
  --mmproj qwen38-27b-heretic-ara-mmproj-f16.gguf \
  -c 32768

The chat template is embedded in the GGUF metadata. It supports reasoning_effort levels xhigh (default), medium, and low, and enable_thinking.

Notes

No MTP tensors. The heretic export drops them, so speculative decoding with the MTP head is not available.
Vision works. The vision tower is untouched by the ablation. Pass the mmproj file with --mmproj.
Quality checks ran on the GPTQ Int4 export of the same ARA weights, not on these GGUF files: GSM8K 92.0% (base quant: 90.5%, same subset, within noise), quality probes 5/5, over-refusal on benign-edgy prompts 0/5, vision correct.
Known quirk: rare, prompt-triggered repetition on long generations (seen once in 9 long-form samples). It is drift-independent in this KL range.

Provenance

Converted from the BF16 ARA export (CorVous/Qwen3.8-27B-heretic-ara-BF16). A GPTQ Int4 W4A16 build of the same weights exists as CorVous/Qwen3.8-27B-heretic-ara-GPTQ-Int4-gs128.

Downloads last month: 911

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CorVous/Qwen3.8-27B-heretic-ara-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(549)

this model