Instructions to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX 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 nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

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 nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

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 nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

Use Docker

docker model run hf.co/nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

Ollama
How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with Ollama:
```
ollama run hf.co/nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
```
Unsloth Desktop

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

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": "nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with Docker Model Runner:
```
docker model run hf.co/nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP
```

Lemonade

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

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 nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP

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 "nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX:Q4_0_ROCMFP" \
  --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 Uncensored — ROCmFP4 STRIX

A Strix Halo-optimized GGUF quantization of the refusal-reduced Qwen3.8-27B model, with its separate MTP/speculative-decoding assistant.

This release targets AMD Strix Halo systems using a ROCmFPX build that supports the custom Q4_0_ROCMFP4_STRIX format. It is not a standard upstream llama.cpp quantization.

Files

File	Format	Size	Purpose
`Qwen3.8-27B-Uncensored-Q4_0_ROCMFP4_STRIX.gguf`	GGUF `Q4_0_ROCMFP4_STRIX`	14,760,069,984 bytes (13.75 GiB)	Main model
`mtp-Qwen3.8-27B-Uncensored-Q4_0.gguf`	GGUF Q4_0	2,034,268,960 bytes (1.89 GiB)	MTP/speculative-decoding assistant
`SHA256SUMS`	SHA-256	—	Checksums for both GGUF files

Total download size is approximately 16.79 GB (15.64 GiB). The MTP file is optional and is not a standalone language model; it requires the matching main model.

This package does not include a vision projector and is intended for text-only serving. The MTP assistant can be omitted when speculative decoding is not wanted.

Usage

Use a recent ROCmFPX build with Qwen3.8/Qwen3.5 hybrid-architecture and MTP (nextn) support. For example:

llama-server \\
  --model Qwen3.8-27B-Uncensored-Q4_0_ROCMFP4_STRIX.gguf \\
  --model-draft mtp-Qwen3.8-27B-Uncensored-Q4_0.gguf \\
  --jinja

The ROCmFP4 STRIX main model was produced and tested with ROCmFPX revision:

c49ebdbd5c9f01ec242369f9e7f7967855f80cba

The MTP assistant was validated locally with the matching main model for speculative drafting. Compatibility with other llama.cpp/ROCmFPX revisions is not guaranteed.

Provenance

Base model: Qwen/Qwen3.8-27B
Refusal-reduced source model: orcarouter/Qwen3.8-27B-Uncensored
Related upstream GGUF releases: orcarouter/Qwen3.8-27B-Uncensored-GGUF
Conversion/runtime project: ROCmFPX

The source model is described by its publisher as an abliterated/refusal-reduced derivative. This repository distributes the associated quantized artifacts and does not claim to reproduce or improve the abliteration method.

Privacy

This repository contains model weights, documentation, and checksums only. No local prompts, conversations, logs, prompt caches, credentials, host paths, or personal files are intentionally included. As with any pretrained model, memorized data from the upstream training corpus cannot be ruled out solely by inspecting the quantized weights.

License and responsible use

The base model is distributed under the Apache License 2.0. The uploader makes no additional license claim beyond the applicable upstream terms. Preserve upstream attribution and license obligations when redistributing these artifacts.

This model has substantially reduced refusal behavior. It is intended for controlled research, red-teaming, interpretability, and guardrail evaluation—not unmoderated public or production deployment. Users are responsible for complying with the license, applicable law, and Hugging Face policies.

Downloads last month: 135

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for nydemeth/Qwen3.8-27B-Uncensored-Q4_0-ROCmFP4-STRIX

Base model

Qwen/Qwen3.8-27B

Quantized

(902)

this model