Instructions to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./llama-cli -hf ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Use Docker

docker model run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

LM Studio
Jan

vLLM

How to use ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Qwen3.8-27B-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": "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-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/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

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

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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": "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ2_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ISTA-DASLab/Qwen3.8-27B-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 ISTA-DASLab/Qwen3.8-27B-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 "ISTA-DASLab/Qwen3.8-27B-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"

Swift-Qwen3.8-27B-GGUF - is it possible to quantize this model?

#37

by GroBmeister - opened 3 days ago

Discussion

GroBmeister

3 days ago

Hey! I understand that there's only so much time in the university to do such a work, but if you'll have a moment, it'd be great to give this distill variant the same treatment: https://huggingface.co/ukisai/Swift-Qwen3.8-27b/tree/main. They released safetensors bf16 weights so no requantising is needed

myhugginfacegacc

2 days ago

•

edited 2 days ago

Definitely looking forward to this! 🙏 Swift-Qwen3.8-27B looks especially interesting because it keeps the reasoning quality while significantly reducing unnecessary thinking. A good GGUF quant for 16GB VRAM would be extremely useful.

qwased

2 days ago

https://huggingface.co/nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2/tree/main/GGUF/Q2-LynnStyle
you can try this.Qwen3.8-27B-EfficientThink-SimPO-Q2-LynnStyle.gguf is also a GSQ-RCO quantization with 3.8bpw

myhugginfacegacc

2 days ago

Thanks for the suggestion! I appreciate it. 🙏

I’m still hoping for a Swift-Qwen3.8-27B quant from ISTA-DASLab, though. From what I’ve seen in the documentation and benchmarks, Swift seems to preserve the original model’s accuracy better while significantly reducing unnecessary thinking. It also looks particularly strong for coding, which is important for us because we want to use it for more sensitive/complex programming tasks.

I’ve tried or looked at quite a few other Qwen3.8 fine-tunes, and some of them show a noticeable drop in accuracy or more errors compared to the original model. Swift seems to be one of the more promising ones in that regard.

So I’m really hoping ISTA-DASLab will quantize Swift using their GSQ-RCO method as well. That would be fantastic! 🙏

Bacongineer

1 day ago

I've been really enjoying the Swift variant! A GSQ-RCO GGUF for it would be amazing 😁

anm2211

IST Austria Distributed Algorithms and Systems Lab org about 22 hours ago

Thank you all for your suggestions! At the moment, we’re putting all of our resources into Flash-Next but we’re also very interested in quantizing custom models created by the community. We can’t give an exact timeline yet but it’s definitely something we’d like to explore.

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