Instructions to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Use Docker

docker model run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Llama new
LM Studio
Jan

vLLM

How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Ollama
How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF with Ollama:
```
ollama run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
```
Unsloth Desktop

How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_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": "ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
```

Lemonade

How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF-IQ1_M

List all available models

lemonade list

Hermes Agent

How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_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 ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-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-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_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 "ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_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"

I think might have had one too many experts stripped out

#11

by Boffy - opened Sep 28

Discussion

Boffy

Sep 28

anm2211

IST Austria Distributed Algorithms and Systems Lab org Sep 28

Thanks for sharing your experiment. Unfortunately, looping can occur with this model and I’ve experienced it as well. We suspect that it may be related to degraded performance at longer context lengths and this is something we’re currently working on improving in future versions.

Could you let me know at what context length you encountered the looping?

Boffy

Sep 29

I think only had like 130k as max context and this part probably in at like 50k

freaxim

Sep 29

You can try to switch to bf16 type for CV cache. It usually helps to reduce looping probability for Qwen family models.
Not yet representative, but yesterday I have several long sessions with this model with 128k context, bf16 keys, q8_0 value cache, without looping

twentieth

Sep 29

•

edited Sep 29

I'll try with--repeat-penalty 1.05 --repeat-last-n 128 and or --dry-multiplier 0.8 if I experience this, and see if it helps.

Also, I wonder what would happen if some layers were repeated, perhaps where layers were removed.

Furcube

12 days ago

It really seems like c# is broken on this model - it does not loop for me, but will start to hallucinate at every turn if i even mention writing c# code. for example tried several times to create c# scaffold with simple code - every time i stopped it after it produced files with mix of c#, java and c++

anm2211

IST Austria Distributed Algorithms and Systems Lab org 12 days ago

Do you still have this problem with the updated model? Because C# is actually one of the programming languages we included in the calibration data. So I’d be happy to know if the issue still persists, as it would help us design better calibration data for future models.

Boffy

12 days ago

the updated model, you only need to update the first large file? ie this one Qwen3.8-Flash-Next-GSQ-RCO-IQ1_M-00001-of-00002.gguf ?

anm2211

IST Austria Distributed Algorithms and Systems Lab org 12 days ago

Yes

Furcube

8 days ago

After some testing i still can't pinpoint exact reason for hallucinations. But i checked on 27B and it sometimes will hallucinate too.
Tried in different harness and could not reproduce. Seems like combination of harness system prompt and my prompt was the cause. C# coding is working just fine.

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