Instructions to use marksverdhei/CoPaw-Flash-9B-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 marksverdhei/CoPaw-Flash-9B-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 marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf marksverdhei/CoPaw-Flash-9B-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 marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

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 marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

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 marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use marksverdhei/CoPaw-Flash-9B-GGUF with Ollama:
```
ollama run hf.co/marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
```

Unsloth Studio

How to use marksverdhei/CoPaw-Flash-9B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for marksverdhei/CoPaw-Flash-9B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for marksverdhei/CoPaw-Flash-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for marksverdhei/CoPaw-Flash-9B-GGUF to start chatting

How to use marksverdhei/CoPaw-Flash-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use marksverdhei/CoPaw-Flash-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marksverdhei/CoPaw-Flash-9B-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 "marksverdhei/CoPaw-Flash-9B-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"

Docker Model Runner
How to use marksverdhei/CoPaw-Flash-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M
```

Lemonade

How to use marksverdhei/CoPaw-Flash-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CoPaw-Flash-9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use marksverdhei/CoPaw-Flash-9B-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 marksverdhei/CoPaw-Flash-9B-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 marksverdhei/CoPaw-Flash-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

CoPaw-Flash-9B GGUF

GGUF quantizations of agentscope-ai/CoPaw-Flash-9B for use with llama.cpp and compatible tools.

Available Quantizations

File	Quant	Size	BPW	Description
`CoPaw-Flash-9B-BF16.gguf`	BF16	17 GB	16.0	Full precision, no quality loss
`CoPaw-Flash-9B-Q8_0.gguf`	Q8_0	8.9 GB	8.5	Near-lossless quantization
`CoPaw-Flash-9B-Q5_K_M.gguf`	Q5_K_M	6.1 GB	5.7	Good balance of quality and size
`CoPaw-Flash-9B-Q4_K_M.gguf`	Q4_K_M	5.3 GB	5.0	Best for constrained hardware

Model Details

Architecture: Qwen3.5 (mixed linear/full attention, 32 layers)
Parameters: ~9B
Context: 262,144 tokens
Base model: Qwen/Qwen3.5-9B
License: Apache 2.0

Usage with llama.cpp

# Download a quantization
huggingface-cli download heiertech/CoPaw-Flash-9B-GGUF CoPaw-Flash-9B-Q4_K_M.gguf

# Run with llama-server
llama-server -m CoPaw-Flash-9B-Q4_K_M.gguf -ngl 99 -fa