Instructions to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./llama-cli -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Use Docker

docker model run hf.co/0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

LM Studio
Jan

vLLM

How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-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": "0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Ollama
How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with Ollama:
```
ollama run hf.co/0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
```
Unsloth Desktop

How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with Docker Model Runner:
```
docker model run hf.co/0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S
```

Lemonade

How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Run and chat with the model

lemonade run user.Qwen3.8-27B-Heretic-GSQ-RCO-GGUF-IQ2_S

List all available models

lemonade list

Hermes Agent

How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

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 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S

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 "0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF:IQ2_S" \
  --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 · GSQ-RCO GGUFs

Non-uniform GGUF quantizations of RVN Qwen3.8-27B-Heretic-Abliterated-Uncensored (refusals 0-1/100, KL ~ 0.0085 vs base). Instead of one uniform quantization type for all tensors, each of the 851 tensors carries its own type, following the per-tensor RCO allocation published by IST-DASLab for their GSQ-RCO release of Qwen3.8-27B, quantized locally with llama.cpp and the official importance matrix imatrix-qwen3.8-27b.gguf. Files are standard GGUF and run unmodified in llama.cpp / Ollama / LM Studio.

Why this release exists

This family was made at the request of community member Heidagger44 in discussion #11:

Regarding IQ3_S there is new method: GSQ-RCO, if it's possible to combine your abliteration method with this quantization, we would have a true refusal free Qwen3.8-27B running fully on 16GB cards.

Thanks for the pointer - this is that combination, in four sizes.

Available files

File	Target bpw	Weights	Notes
`RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ2_XS.gguf`	2.50	8.45 GB	Smallest tier - 12 GB-class cards
`RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ2_S.gguf`	2.75	9.28 GB	Balanced low-memory tier
`RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ3_XXS.gguf`	3.00	10.12 GB	Strong sub-10.5 GB operating point
`RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ3_S.gguf`	3.50	11.80 GB	Recommended on 16 GB cards
4 x `*-mtp.gguf` twins	-	+0.42 GiB each	Embedded official Qwen3.8 MTP/NextN head; main weights identical

Quality - measured, not assumed

Perplexity on wikitext-2 (llama-perplexity, ctx 4096, one RTX PRO 6000 Blackwell, full offload):

Variant	PPL (wikitext-2)	Delta vs F16
F16 reference (`RVN-F16.gguf`)	6.1197	-
GSQ-RCO IQ3_S	6.1778	+0.95%
GSQ-RCO IQ3_XXS	6.3486	+3.7%
GSQ-RCO IQ2_S	6.5058	+6.3%
GSQ-RCO IQ2_XS	6.7724	+10.7%
A/B: uniform `RVN-IQ3_S.gguf`	6.2956	+2.9%

At 3.50 bpw the allocation lands within 1% of F16 - and a same-class uniform quantization sits 1.9% behind it at a larger file size (12.42 GB vs 11.80 GB). Generation speeds (same box, full offload): IQ2_XS 105 t/s, IQ2_S 101 t/s, IQ3_XXS 97 t/s, IQ3_S 90 t/s, IQ3_S-mtp 150 t/s with --spec-type draft-mtp.

How these files were built

Allocation - IST-DASLab's published per-tensor RCO maps for this tier set (851 tensor-to-type entries each; targets 2.50-3.50 bpw).
Quantization - every tensor of RVN-F16.gguf quantized at its assigned type with llama.cpp (--tensor-type-file), using the official imatrix-qwen3.8-27b.gguf.
MTP embedding - the official Qwen3.8 MTP/NextN head (from mtp-RVN.gguf) raw-byte merged into the -mtp twins (block_count=65, nextn_predict_layers=1).

Exactness - header audit per file: 803/851 tensors match the published allocation exactly; the 48 ssm_alpha tensors are held at F32 by llama.cpp's SSM precision rule (the map lists BF16 - strictly higher precision, ~ +24 MB/file).

Provenance note - this reproduces the RCO allocation with optimized local quantization. The per-tensor GSQ refinement pass from ISTA's internal pipeline is not reproduced; its current public implementation is a research checkpoint that regresses end-to-end KL in its own tests. The allocation and the official importance matrix are the published, verifiable ingredients. If the KL-gated refinement lands upstream we will re-run it.

Usage

# 16 GB cards: start here
llama-cli -m RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ3_S.gguf -ngl 99 --temp 1.0 -p "Your prompt"

# speculative decoding with the embedded MTP head (llama.cpp >= b10440):
llama-cli -m RVN-Qwen3.8-27B-Heretic-GSQ-RCO-IQ3_S-mtp.gguf -ngl 99 \
  --spec-type draft-mtp --spec-draft-n-max 2 --parallel 1 -p "Your prompt"

Thinking mode follows the model's chat template. A vLLM/Transformers (compressed-tensors) GSQ variant lives in the companion repository under GSQ-3bit/.

Related repositories

Main model + standard quant spectrum: Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF
FP16 safetensors (vLLM/SGLang): Qwen3.8-27B-Heretic-Abliterated-Uncensored

Credits

Per-tensor RCO allocation + official importance matrix: IST-DASLab (GSQ-RCO release). Quantization, verification, and MTP embedding: this repository. Base abliteration (RVN / ARA): see the main repository.

Downloads last month: 6,600

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

Model tree for 0bserverx/Qwen3.8-27B-Heretic-GSQ-RCO-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

Finetuned

0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored

Quantized

(3)

this model