Instructions to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

Use Docker

docker model run hf.co/Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cyronius/Qwen3.8-Flash-Next-131B-A6B-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": "Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

Ollama
How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with Ollama:
```
ollama run hf.co/Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
```
Unsloth Desktop

How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

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": "Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with Docker Model Runner:
```
docker model run hf.co/Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0
```

Lemonade

How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-131B-A6B-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

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 Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0

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 "Cyronius/Qwen3.8-Flash-Next-131B-A6B-GGUF:Q4_0" \
  --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"

how to do this: table fully deleted (0/16)

by rosspanda0 - opened 23 days ago

Discussion

rosspanda0

23 days ago

just delete the corresponding weights? can the model still work?

Cyronius

Owner 20 days ago

yep! One of my tests deleted all of the weights and it still works, though suffers a bit for it. But just keeping a tiny amount is a good compromise. Note that I removed these indiscriminately; if one were to actually test with real workloads and see which ones activate, you could delete them more intelligently than i have, keep a small core that punches above its weight, and outperform the quick benchmarks I posted. Or maybe they are already in the imat matrix???

The code I used to do this is all at my github at https://github.com/Cyronius/qwen-prune-heal-pipeline . You could very easily pull this down, feed the request into your agent, and replicate/improve what I've done. Since I didn't do any retraining this is something you can do on a normal PC, big requirement is to have enough disk space. I literally just took the unsloth versions and used that pipeline to cut it down.

Atomic-Germ

13 days ago

@Cyronius Oh shit here you are in the wild

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