Instructions to use bartowski/Qwen3.8-Flash-Next-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 bartowski/Qwen3.8-Flash-Next-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 bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_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 bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use bartowski/Qwen3.8-Flash-Next-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Qwen3.8-Flash-Next-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": "bartowski/Qwen3.8-Flash-Next-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/bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Ollama
How to use bartowski/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bartowski/Qwen3.8-Flash-Next-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_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": "bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bartowski/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/Qwen3.8-Flash-Next-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bartowski/Qwen3.8-Flash-Next-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 bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_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 bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bartowski/Qwen3.8-Flash-Next-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_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 "bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_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"

Quants, their size and performance. Q5_K_M or Q4_K_L?

by MetaphoricalCode - opened Sep 1

Discussion

MetaphoricalCode

Sep 1

Hey! Thank you for your quants, as always. Yours are usually my go-to.

I've got a question regarding quantization of this particular model, with new N-grams and such. Do you think quantization of per_layer_token_embd.weight layer matters a lot?

Your Q5_K_S and Q5_K_M quants weight less than Q4_K_L because the latter leaves per_layer_token_embd.weight in Q8_0. Do you think it affects the performance? Have you perhaps done KLD tests or got any other data regarding the matter?

Honestly I'm just trying to understand the better approach for this model's architecture. Should I use Q5_K_M quant or Q4_K_L, given they're almost the same size? Basically it's a choice prioritizing quantization for per_layer_token_embd.weight or for other layers. I haven't been able to find any data on that regard so far. With probably more models using N-grams in the future, it would be great to understand.

Dr-Ojinsky

Sep 4

ALLWAYS get 5bit if your gpu can run it. Don't even ask.

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