Instructions to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

Use Docker

docker model run hf.co/TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

LM Studio
Jan

vLLM

How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-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": "TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-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/TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

Ollama
How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with Ollama:
```
ollama run hf.co/TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
```
Unsloth Desktop

How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

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": "TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with Docker Model Runner:
```
docker model run hf.co/TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16
```

Lemonade

How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

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 TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16

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 "TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF:F16" \
  --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"

It's working great!

by AugustHell - opened 5 days ago

Discussion

AugustHell

5 days ago

I just want to thank you for making this quant public, it is awesome!
I've got a RTX 3060 with 12gb and the last two months I tried to solve problems I was facing with almost any capable model (qwen 3.5/3.6, gemma 4, glm 4.7): Loops, errors writing big files, bad reasoning. I tried many things to get around to get finally something I can work with an hermes or pi agent and tried out a lot of llms on the way. This now solved any problem, it works exceptionally good out of the box! No looping, no file write problems and much better reasoning for my works.
I'm using the unsloth studio api (llama.cpp based) with this cli command:
unsloth run -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF -c 65536 -n 8192 --parallel 1 -ngl 999 -b 512 -ub 512 --cache-type-k q4_0 --cache-type-v q4_0 -fa on --temp 1 --top-p 0.95 --top-k 20 --min-p 0.0 --chat-template-kwargs "{"reasoning_effort":"low"}" --reasoning on --reasoning-effort low

TheWegemann

Owner 5 days ago

I just want to thank you for making this quant public, it is awesome!
I've got a RTX 3060 with 12gb and the last two months I tried to solve problems I was facing with almost any capable model (qwen 3.5/3.6, gemma 4, glm 4.7): Loops, errors writing big files, bad reasoning. I tried many things to get around to get finally something I can work with an hermes or pi agent and tried out a lot of llms on the way. This now solved any problem, it works exceptionally good out of the box! No looping, no file write problems and much better reasoning for my works.
I'm using the unsloth studio api (llama.cpp based) with this cli command:
unsloth run -hf TheWegemann/Qwen3.8-27B-LowGPU-NoMTP-IQ3XXXS-GGUF -c 65536 -n 8192 --parallel 1 -ngl 999 -b 512 -ub 512 --cache-type-k q4_0 --cache-type-v q4_0 -fa on --temp 1 --top-p 0.95 --top-k 20 --min-p 0.0 --chat-template-kwargs "{"reasoning_effort":"low"}" --reasoning on --reasoning-effort low

Thank you so much for the feedback — this honestly made my day. 😊
Knowing that it works well on a 12 GB RTX 3060, especially for Hermes/Pi agent workflows, is exactly the kind of real-world result I hoped for when making this quant public.
And thanks for sharing your command/settings too — that’s really useful for other users. Glad the weird little IQ3XXXS monster is behaving itself. 😄
Have fun with it, and feel free to report anything interesting you notice!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment