Instructions to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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": "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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/sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M

SGLang

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with Ollama:
```
ollama run hf.co/sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M
```
Unsloth Desktop

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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": "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with Docker Model Runner:
```
docker model run hf.co/sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M
```

Lemonade

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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 "sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-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"

Minecraft Agent Qwen3.5-9B Stage 3 GGUF

This repository provides GGUF quantizations and multimodal vision projector weights for EmberJin/Minecraft-Agent-Qwen3.5-9B-Stage3.

Minecraft Agent is an embodied vision-language agent trained on 200,000+ human gameplay trajectories (6 million frames at 20 FPS, 640x360 resolution) to play Minecraft directly from raw first-person pixels and output structured text actions.

All GGUF files were converted from the original safetensors weights using llama.cpp at native BF16 precision, then quantized into standard k-quant variants. The vision projector is provided as a standalone mmproj file for multimodal inference.

Available Files and Quantizations

File	Quant Type	Size	Description / Recommendation
`Minecraft-Agent-Qwen3.5-9B-Stage3-BF16.gguf`	BF16	16.69 GB	Full precision base text model. Highest fidelity reference weights.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q8_0.gguf`	Q8_0	8.87 GB	Near-lossless 8-bit quantization. Recommended for critical precision.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q6_K.gguf`	Q6_K	6.85 GB	High quality retention with minimal degradation. Excellent balance.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q5_K_M.gguf`	Q5_K_M	6.02 GB	Good balance between memory usage and action prediction accuracy.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q4_K_M.gguf`	Q4_K_M	5.24 GB	Fast, lightweight 4-bit quant. Recommended default for agent rollouts.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q3_K_M.gguf`	Q3_K_M	4.31 GB	Compact footprint when GPU or system memory headroom is limited.
`Minecraft-Agent-Qwen3.5-9B-Stage3-Q2_K.gguf`	Q2_K	3.56 GB	Maximum compression for testing on low-memory hardware.
`mmproj-Minecraft-Agent-Qwen3.5-9B-Stage3-BF16.gguf`	BF16 (Vision)	0.86 GB	Multimodal projector (27-layer ViT vision tower + projector). Required for image/frame inputs.

Technical Specifications

Base Architecture: Qwen3_5ForConditionalGeneration (model_type: qwen3_5)
Text Backbone: qwen3_5_text (32 hidden layers, DeltaNet linear attention + full attention)
Vision Tower: qwen3_5_vision (27-layer ViT, patch size 16, spatial merge size 2, hidden size 1152)
Parameters: ~9B active
Context Length: Up to 32,768 tokens
Action Space: Continuous mouse movements (dx, dy), discrete key presses, and mouse clicks
Native Precision: bfloat16
License: Apache 2.0

Action Format and Prompting

The agent consumes a sliding window of frames (recommended: 29 history frames + 1 current frame) and outputs structured text actions:

Action: move(dx, dy) and press(keys...) [and click(button)]

Examples

Walking forward and turning right: Action: move(0.5, -0.3) and press(w)
Mining a block in place: Action: move(0, 0) and press() and click(left)
Jumping while sprinting forward: Action: move(0, 0) and press(w, space)

Turn Structure

The first user turn supplies the system prompt, task instruction, and initial frame. Subsequent turns provide image-only user messages alternating with assistant action predictions.

Benchmark Results (easy-ng)

Evaluated on the easy-ng benchmark across 202 non-GUI tasks (153 Embodied mine_block + 49 Combat kill_entity), 3 rollouts per task, difficulty easy, 200-step episodes:

Inference History Window	Overall Success Rate	Embodied Tasks	Combat Tasks
3 frames (baseline)	15.0%	17.9%	6.2%
29 frames (training match)	24.9%	24.8%	25.2%

How to Use

1. With llama.cpp

For multimodal generation with raw gameplay screenshots, pass both the quantized model and the mmproj file:

llama-qwen2vl-cli \
    -m ./Minecraft-Agent-Qwen3.5-9B-Stage3-Q4_K_M.gguf \
    --mmproj ./mmproj-Minecraft-Agent-Qwen3.5-9B-Stage3-BF16.gguf \
    --image ./gameplay_frame.png \
    -p "Mine the wood block directly ahead." \
    -n 64

For text-only testing or action syntax verification:

llama-cli -m ./Minecraft-Agent-Qwen3.5-9B-Stage3-Q4_K_M.gguf \
    -p "<|im_start|>system\nYou are an embodied Minecraft agent.<|im_end|>\n<|im_start|>user\nMine a tree block in front of you.<|im_end|>\n<|im_start|>assistant\nAction: " \
    -n 32

Launch an OpenAI-compatible multimodal server:

llama-server \
    -m ./Minecraft-Agent-Qwen3.5-9B-Stage3-Q4_K_M.gguf \
    --mmproj ./mmproj-Minecraft-Agent-Qwen3.5-9B-Stage3-BF16.gguf \
    --port 8080 \
    -c 16384 \
    --host 0.0.0.0

2. With Ollama

Create a file named Modelfile:

FROM ./Minecraft-Agent-Qwen3.5-9B-Stage3-Q4_K_M.gguf
MMPROJ ./mmproj-Minecraft-Agent-Qwen3.5-9B-Stage3-BF16.gguf

TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{- end }}
{{- range .Messages }}
<|im_start|>{{ .Role }}
{{ .Content }}<|im_end|>
{{- end }}
<|im_start|>assistant
Action: 
"""

PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"
PARAMETER temperature 0.2
PARAMETER top_p 0.9

Build and run:

ollama create minecraft-agent -f Modelfile
ollama run minecraft-agent

Limitations

GUI tasks such as crafting tables, furnace smelting, and chest sorting are out of scope (the model operates strictly on pixel-to-motor control and lacks inventory GUI coordinate grounding).
Optimal execution requires a sliding history of up to 29 frames to maintain behavioral momentum.

License

This model is licensed under Apache 2.0, inheriting upstream licensing from Qwen/Qwen3.5-9B. See the LICENSE file for details.

Downloads last month: 348

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for sizzlebop/Minecraft-Agent-Qwen3.5-9B-Stage3-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

EmberJin/Minecraft-Agent-Qwen3.5-9B-Stage3

Quantized

(1)

this model