Instructions to use cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M

Use Docker

docker model run hf.co/cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use cvgro/Qwen3.8-27B-ABLITERATED-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cvgro/Qwen3.8-27B-ABLITERATED-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": "cvgro/Qwen3.8-27B-ABLITERATED-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M

Ollama
How to use cvgro/Qwen3.8-27B-ABLITERATED-GGUF with Ollama:
```
ollama run hf.co/cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M
```
Unsloth Desktop

How to use cvgro/Qwen3.8-27B-ABLITERATED-GGUF with Pi:

Start the llama.cpp server

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

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": "cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use cvgro/Qwen3.8-27B-ABLITERATED-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-ABLITERATED-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-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 cvgro/Qwen3.8-27B-ABLITERATED-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cvgro/Qwen3.8-27B-ABLITERATED-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cvgro/Qwen3.8-27B-ABLITERATED-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 "cvgro/Qwen3.8-27B-ABLITERATED-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-ABLITERATED-GGUF / deploy /DEPLOYMENT.md

cvgro

Duplicate from Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF

72c1456 14 days ago

preview code

Raw

History Blame Contribute Delete

3.26 kB

Qwen3.8-27B-ABLITERATED-GGUF deployment

This kit serves the public, ungated GGUF release with a current llama-server build. The default is Q4_K_M, 16,384 tokens of context, full GPU offload, and text-only operation.

Requirements

A recent build of llama.cpp with llama-server
Python and the Hugging Face CLI: pip install -U huggingface_hub
Enough combined RAM/VRAM for the selected quant, context state, compute buffers, and optional vision projector

The architecture advertises 262,144 tokens, but context allocation is a deployment choice. Start at 16K, measure memory at the desired concurrency, and scale deliberately.

One-command launch

chmod +x deploy/serve.sh
./deploy/serve.sh

The server listens on port 8080 and exposes the OpenAI-compatible API. The public repository requires no Hugging Face token.

Select a quant

QUANT=Q5_K_M ./deploy/serve.sh

Accepted standard ladder values are:

Q2_K Q3_K_S Q3_K_M Q4_K_S Q4_K_M Q5_K_S Q5_K_M Q6_K Q8_0

Q4_K_M is the recommended starting point. No IQ/IK or importance-matrix quants are part of this release.

Enable vision and video inputs

ENABLE_VISION=1 ./deploy/serve.sh

This downloads and loads the compact Q8_0 projector. Select the full projector with:

ENABLE_VISION=1 MMPROJ_TYPE=F16 ./deploy/serve.sh

CPU-only and hybrid inference

CPU-only:

GPU_LAYERS=0 ./deploy/serve.sh

For hybrid inference, choose a positive GPU_LAYERS value that fits the available VRAM. Model weights not offloaded to the GPU remain in system RAM.

Context and network settings

CTX_SIZE=32768 HOST=127.0.0.1 PORT=8080 ./deploy/serve.sh

Bind to a private interface or place the endpoint behind authenticated infrastructure for shared use. The model and its embedded prompt are not an access-control boundary.

Direct llama-server launch

llama-server \
  -m Qwen3.8-27B-ABLITERATED-Q4_K_M.gguf \
  --mmproj mmproj-Qwen3.8-27B-ABLITERATED-Q8_0.gguf \
  -ngl 999 -fa on --jinja \
  --host 0.0.0.0 --port 8080 -c 16384 \
  --temp 1.0 --top-p 0.95 --top-k 20

Keep --jinja enabled: the GGUF contains the release's default Blackfrost system template. A client-supplied system message is additive to that embedded default.

API smoke test

curl http://127.0.0.1:8080/health

curl http://127.0.0.1:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "Qwen3.8-27B-ABLITERATED",
    "messages": [{"role": "user", "content": "Reply with exactly READY and nothing else."}],
    "temperature": 0,
    "max_tokens": 64
  }'

Reasoning-capable responses may include reasoning_content separately from final content. Allow enough output tokens for workloads that use the reasoning channel.

Operational checklist

Pin a tested llama.cpp build in production.
Record quant, context, sampler, template, and projector in benchmark reports.
Authenticate shared endpoints and log tool execution independently.
Sandbox code and file tools and grant them least-privilege credentials.
Test structured output, tools, multimodal inputs, and long context separately before relying on them.