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"

request for qwen3.8 next

by Chillzyg - opened 22 days ago

Discussion

Chillzyg

22 days ago

can we get a gsq rco quantization fot the next model

anm2211

IST Austria Distributed Algorithms and Systems Lab org 22 days ago

Yes, definitely. Once we’re done with Qwen3.8-27B, we’re going to work on GSQ-RCO quantization for the flash-next model as well. Thanks for the suggestion!

differentiator

22 days ago

Yes, definitely. Once we’re done with Qwen3.8-27B, we’re going to work on GSQ-RCO quantization for the flash-next model as well. Thanks for the suggestion!

I can test it on 32GB VRAM 5090 and 128 GB RAM if that may be helpful.

anm2211

IST Austria Distributed Algorithms and Systems Lab org 21 days ago

That’d be awesome, thanks! I’d definitely be interested in seeing how it runs on your setup once our quants are ready.

11011Free

18 days ago

•

edited 18 days ago

An interesting idea, this will cause the ceo of chatgpt to collapse in shock as if he were seeing a nuclear bomb explode
Oh, by the way, I've noticed that some friends have cut off the non-code expert feature of qwen3.8-next and still managed to run coding tasks normally. Could we consider a fully functional iq3_s and a quantized version of iq3_s with only coding function cuts?

anm2211

IST Austria Distributed Algorithms and Systems Lab org 17 days ago

For our first release we’re aiming for a general-purpose ~38 GB model (excluding the N-gram table). That said this is a very interesting suggestion. Expert pruning is one of the areas where RCO can perform particularly well, and it’s something we haven’t explored yet.

Chillzyg

17 days ago

38gb thats whithin the 3 ish bpw while still lossless on tasks thats crazy. i cant wait to try it on a new solution im working on for low vram machines !!! (experts multi external ssd streaming), im trying to see how much speed i can still get. but i think ill have to customize the backend for the model when it comes out.

11011Free

17 days ago

•

edited 17 days ago

For our first release we’re aiming for a general-purpose ~38 GB model (excluding the N-gram table). That said this is a very interesting suggestion. Expert pruning is one of the areas where RCO can perform particularly well, and it’s something we haven’t explored yet.

qwen3.8-27b and qwen3.8-next might both be specialized versions for the coding field. In fact, I only use them to write code, and most people probably do the same. So, eliminating other expert layers is not a problem. As for those who want to use them to write articles or make PPTS, Any other 9B small model can handle it.
By the way, in fact, relying on ai for everything is an extremely dangerous thing. It will gradually lose one's own thinking ability. People should still occasionally write articles and take notes by themselves to maintain the joy of creating something with their own hands. Otherwise, they will only become physical puppets of agents. Handing over the code to qwen3.8 was a choice made out of necessity to reduce the intensity of labor.
Thank you for your work. Good luck to you~

11011Free

16 days ago

•

edited 16 days ago

Hey bros, this is the expert-pruned version of Qwen3.8-Flash-Next:

https://huggingface.co/ranxianglei/Qwen3.8-Flash-Next-W4A16-Modular
https://github.com/ranxianglei/sglang/blob/ours/main/README.zh-CN.md
https://github.com/ranxianglei/sglang-expert-profile/blob/main/README.zh-CN.md

We hope to leverage the collective power of the entire community to create expert-layer profile descriptions for all expert layers in both Qwen3.8-27B and Qwen3.8-flash-next. This way, everyone can later freely combine the experts they need from these two models to create domain-specific models.
Then, combined with IQ3_S quantization, we can obtain minimal-size, domain-specialized quantized models that retain Qwen3.8's intelligence.
The author is also the creator of the billion-context project https://github.com/ranxianglei/billion-context/tree/master. Combined with this plugin, agents can maintain just 100K context per session while still handling long-conversation tasks.

The final goal is that both Qwen3.8-27B and Qwen3.8-Flash-Next can have 3-bit or 2-bit quantized, domain-specialized mini-models for each field, to assemble a team of expert agents for different tasks.

TomLucidor

13 days ago

@anm2211 requesting this method for Gemma series as well (for prose especially for the E4B series) and Ling 3.0 series (less relative compute) and the other Qwen3.5/3.6 sizes for small models to experience the speed-up

ReingeFallen

11 days ago

I can test your models on my setup aswell. I have a RTX 3060 (12gb), RTX 5090 (32GB) and 192GB RAM.

gopi87

9 days ago

i can test it too i have own pr too for my server i am currently using q8 and its smarts

differentiator

7 days ago

@anm2211 do you have an ETA for this release? I am constantly refreshing the pages to get any update

anm2211

IST Austria Distributed Algorithms and Systems Lab org 7 days ago

Unfortunately, not yet. I’ve been working on this day and night and we want to make sure it meets our quality standards before releasing it. I’ll announce it here as soon as it’s released so you’ll get a notification.

anm2211

IST Austria Distributed Algorithms and Systems Lab org 6 days ago

Qwen3.8-Flash-Next GSQ-RCO GGUF models are finally released! We’ll be adding two more bitwidths over the coming days.

@differentiator @ReingeFallen @gopi87
We would have loved to give you early access for testing but unfortunately we ran into some issues with HF and weren’t able to upload the models to a private repository. In any case, I want to thank all of you for offering to test the models and for your patience while we were working on the release. We really appreciate the enthusiasm and support!

Now that the models are public we’d still love to hear how they perform on your setups. Any feedback on quality, speed, memory usage, or issues you encounter would be extremely helpful.

Thanks again and hope you enjoy the models! ❤️

gopi87

6 days ago

Qwen3.8-Flash-Next GSQ-RCO GGUF models are finally released! We’ll be adding two more bitwidths over the coming days.

@differentiator @ReingeFallen @gopi87
We would have loved to give you early access for testing but unfortunately we ran into some issues with HF and weren’t able to upload the models to a private repository. In any case, I want to thank all of you for offering to test the models and for your patience while we were working on the release. We really appreciate the enthusiasm and support!

Now that the models are public we’d still love to hear how they perform on your setups. Any feedback on quality, speed, memory usage, or issues you encounter would be extremely helpful.

Thanks again and hope you enjoy the models! ❤️

thanks for the release i will test it and share it btw i have seperate pr for running the qwen next flash for higer ub and b with lower vram anyone interested kindly check it
https://github.com/ggml-org/llama.cpp/pull/28623

differentiator

5 days ago

•

edited 5 days ago

Qwen3.8-Flash-Next GSQ-RCO GGUF models are finally released! We’ll be adding two more bitwidths over the coming days.

@differentiator @ReingeFallen @gopi87
We would have loved to give you early access for testing but unfortunately we ran into some issues with HF and weren’t able to upload the models to a private repository. In any case, I want to thank all of you for offering to test the models and for your patience while we were working on the release. We really appreciate the enthusiasm and support!

Now that the models are public we’d still love to hear how they perform on your setups. Any feedback on quality, speed, memory usage, or issues you encounter would be extremely helpful.

Thanks again and hope you enjoy the models! ❤️

Great release! I think this is the best model so far I had been running locally, both from quality and performance perspective

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