Instructions to use miniHui/Geo-R1-Q3-Q8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use miniHui/Geo-R1-Q3-Q8-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="miniHui/Geo-R1-Q3-Q8-GGUF",
	filename="Geo-R1-Q3_K_M.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use miniHui/Geo-R1-Q3-Q8-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 miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf miniHui/Geo-R1-Q3-Q8-GGUF:Q3_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 miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf miniHui/Geo-R1-Q3-Q8-GGUF:Q3_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 miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M

Use Docker

docker model run hf.co/miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use miniHui/Geo-R1-Q3-Q8-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miniHui/Geo-R1-Q3-Q8-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": "miniHui/Geo-R1-Q3-Q8-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/miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M

Ollama
How to use miniHui/Geo-R1-Q3-Q8-GGUF with Ollama:
```
ollama run hf.co/miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
```

Unsloth Studio

How to use miniHui/Geo-R1-Q3-Q8-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 miniHui/Geo-R1-Q3-Q8-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 miniHui/Geo-R1-Q3-Q8-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for miniHui/Geo-R1-Q3-Q8-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use miniHui/Geo-R1-Q3-Q8-GGUF with Docker Model Runner:
```
docker model run hf.co/miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M
```

Lemonade

How to use miniHui/Geo-R1-Q3-Q8-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull miniHui/Geo-R1-Q3-Q8-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.Geo-R1-Q3-Q8-GGUF-Q3_K_M

List all available models

lemonade list

Geo-R1 Q3 + Q8 GGUF

This repo is proudly made by TerraByte AI.

Compact GGUF conversion of miniHui/Geo-R1, a geospatial reasoning model based on Qwen2.5-VL-7B-Instruct.

Files

File	Format	Size	SHA-256
`Geo-R1-Q3_K_M.gguf`	Q3_K_M language model (3.99 BPW)	3,808,389,984 bytes	`ac7f05c206193fbc548b919b7a3440e6904b4cd875f91dcb0e13d103af82fcb0`
`mmproj-Geo-R1-Q8_0.gguf`	Q8_0 vision projector	856,130,560 bytes	`98ef33cf4d85f8f73ad8b3572a4368d1070e0e101d9fb74e21f1bb78e5a30604`

Q3_K_M is a mixed K-quant format averaging 3.99 bits per weight. The vision projector uses Q8_0 while retaining higher precision for sensitive position embeddings, normalization weights, and biases. Both files are required for image or video inputs.

Usage

Use a recent llama.cpp build:

llama-cli \
  -m Geo-R1-Q3_K_M.gguf \
  --mmproj mmproj-Geo-R1-Q8_0.gguf \
  --image /path/to/image.jpg \
  -p "Analyze this image and explain your reasoning."

Conversion and validation

Converted directly from the BF16 GGUF with llama.cpp revision 86a9c79f866799eb0e7e89c03578ccfbcc5d808e.

The Q3_K_M language model was validated with text generation. The Q3_K_M and Q8_0 pair was also validated with a real image prompt; llama.cpp detected the text, vision, and video modalities and produced a correct image description.

See the original model card for model details, intended use, and attribution.

Downloads last month: 4

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

3-bit

Model tree for miniHui/Geo-R1-Q3-Q8-GGUF

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

miniHui/Geo-R1

Quantized

(6)

this model