Instructions to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF with Ollama:
```
ollama run hf.co/MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
```
Unsloth Desktop

How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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": "MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF with Docker Model Runner:
```
docker model run hf.co/MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M
```

Lemonade

How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen-3.5-0.8b-Hedgehog-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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 "MichaelAnthony/qwen-3.5-0.8b-Hedgehog-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"

qwen-3.5-0.8b-Hedgehog GGUF r5

GGUF builds of the accepted r5 starter release. Every file was inspected as a 24-block qwen35 model with 320 tensors and independently loaded through llama.cpp ROCm. All four formats produced exact 7/7-field JSON in the release invoice smoke test.

File	Size	SHA-256
`qwen-3.5-0.8b-Hedgehog.F16.gguf`	1,516,744,064	`b3fb5a844cf7f7d2024916e366e767e89f4ca664c008a3528a919787b546dbf0`
`qwen-3.5-0.8b-Hedgehog.Q4_K_M.gguf`	529,296,768	`04fa8f6c59820043a806b695e5238d91980388615d2105ded5d87aee38306442`
`qwen-3.5-0.8b-Hedgehog.Q6_K.gguf`	629,743,488	`4b2279c6009edb9590867e204f86537a55ded264f4f396f229165f3159d43186`
`qwen-3.5-0.8b-Hedgehog.Q8_0.gguf`	811,842,944	`009c05a62bb642840f79efdf802a73d79b1a1070d10913a86c4ca400b344f070`

Use Q6_K; Q6_K_0 is not a supported quantization name in the verified llama.cpp toolchain. For deterministic extraction, use temperature 0 and disable thinking. See the main Transformers repository for the complete r5 evaluation and known limitations.

Downloads last month: 361

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MichaelAnthony/qwen-3.5-0.8b-Hedgehog-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

MichaelAnthony/qwen-3.5-0.8b-Hedgehog

Quantized

(1)

this model