Instructions to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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": "SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M

Ollama
How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with Ollama:
```
ollama run hf.co/SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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": "SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M
```

Lemonade

How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-minecraft-distill-v1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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 "SebastianAldrin/Qwen3.5-9B-minecraft-distill-v1-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"

SebastianAldrin commited on Jul 20

Commit

88d73ea

verified ·

1 Parent(s): 9ff9b5a

Link the Agent Society repo; point the dataset link at the current username

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -22,7 +22,8 @@ runs locally and offline instead of calling a frontier model every tick.
 | Base | `Qwen/Qwen3.5-9B` |
 | Method | LoRA SFT — rank 16, alpha 32, dropout 0.05, all-linear, 3 epochs |
 | Teacher | Claude Sonnet |
-| Data | [Chanito91/agent-society-distill-v1](https://huggingface.co/datasets/Chanito91/agent-society-distill-v1) — 1,355 examples |
 | Format | GGUF, **Q4_K_M** (~5.4 GB) — runs in llama.cpp / Ollama |
 Given the agent's situation as a prompt (felt needs, a local block-map, bearings, the
@@ -39,7 +40,7 @@ llama-server -m Qwen3.5-9B-minecraft-distill-v1-Q4_K_M.gguf -c 8192 --jinja
 Send the decide prompt with `enable_thinking: false` and a JSON-schema response format
 (the model is trained to answer with the decision JSON only). Full system prompt and
-prompt format live in the Agent Society repository.
 On CUDA, add `--flash-attn off` — llama.cpp's `auto` default silently corrupts this
 hybrid-SSM architecture: the JSON shape survives but the words inside turn to noise.
@@ -52,7 +53,7 @@ hybrid-SSM architecture: the JSON shape survives but the words inside turn to no
 - The prompt isn't cacheable on this arch, so it re-reads the whole prompt every tick.
   Slow on a weak GPU or CPU.
 - Measured: on 250 held-out teacher decisions it picks the teacher's action **78.0%**
-  of the time; the untuned base scores 56.8%. Method in the repo's evaluation doc.
 ## License

 | Base | `Qwen/Qwen3.5-9B` |
 | Method | LoRA SFT — rank 16, alpha 32, dropout 0.05, all-linear, 3 epochs |
 | Teacher | Claude Sonnet |
+| Data | [SebastianAldrin/agent-society-distill-v1](https://huggingface.co/datasets/SebastianAldrin/agent-society-distill-v1) — 1,355 examples |
+| Code | [Agent Society](https://github.com/sebastianaldrin/agent-society) |
 | Format | GGUF, **Q4_K_M** (~5.4 GB) — runs in llama.cpp / Ollama |
 Given the agent's situation as a prompt (felt needs, a local block-map, bearings, the
 Send the decide prompt with `enable_thinking: false` and a JSON-schema response format
 (the model is trained to answer with the decision JSON only). Full system prompt and
+prompt format live in the [Agent Society repository](https://github.com/sebastianaldrin/agent-society).
 On CUDA, add `--flash-attn off` — llama.cpp's `auto` default silently corrupts this
 hybrid-SSM architecture: the JSON shape survives but the words inside turn to noise.
 - The prompt isn't cacheable on this arch, so it re-reads the whole prompt every tick.
   Slow on a weak GPU or CPU.
 - Measured: on 250 held-out teacher decisions it picks the teacher's action **78.0%**
+  of the time; the untuned base scores 56.8%. Method in the [evaluation doc](https://github.com/sebastianaldrin/agent-society/blob/main/docs/evaluation.md).
 ## License