Instructions to use Mungert/MinerU2.5-2509-1.2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mungert/MinerU2.5-2509-1.2B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mungert/MinerU2.5-2509-1.2B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mungert/MinerU2.5-2509-1.2B-GGUF", dtype="auto")

llama-cpp-python

How to use Mungert/MinerU2.5-2509-1.2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mungert/MinerU2.5-2509-1.2B-GGUF",
	filename="MinerU2.5-2509-1.2B-bf16.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 Mungert/MinerU2.5-2509-1.2B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Mungert/MinerU2.5-2509-1.2B-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 Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mungert/MinerU2.5-2509-1.2B-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 Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Mungert/MinerU2.5-2509-1.2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mungert/MinerU2.5-2509-1.2B-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": "Mungert/MinerU2.5-2509-1.2B-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/Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M

SGLang

How to use Mungert/MinerU2.5-2509-1.2B-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 "Mungert/MinerU2.5-2509-1.2B-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": "Mungert/MinerU2.5-2509-1.2B-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 "Mungert/MinerU2.5-2509-1.2B-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": "Mungert/MinerU2.5-2509-1.2B-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 Mungert/MinerU2.5-2509-1.2B-GGUF with Ollama:
```
ollama run hf.co/Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use Mungert/MinerU2.5-2509-1.2B-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 Mungert/MinerU2.5-2509-1.2B-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 Mungert/MinerU2.5-2509-1.2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mungert/MinerU2.5-2509-1.2B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Mungert/MinerU2.5-2509-1.2B-GGUF with Docker Model Runner:
```
docker model run hf.co/Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M
```

Lemonade

How to use Mungert/MinerU2.5-2509-1.2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mungert/MinerU2.5-2509-1.2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MinerU2.5-2509-1.2B-GGUF-Q4_K_M

List all available models

lemonade list

mmproj 是否可以量化到 Q4，对效果损失多大？

by openmartin - opened Oct 20, 2025

Discussion

openmartin

Oct 20, 2025

CPU 上跑还是很慢，一张图100秒以上

Mungert

Owner Oct 21, 2025

This comment has been hidden

Mungert

Owner Oct 21, 2025

There is no support for q4 when using llama.cpp to make projector file. q8 is the smallest.

100s is normal. There are a lot of tokens created from an image.

Mungert

Owner Oct 21, 2025

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

openmartin

Oct 21, 2025

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

thanks，you are right.
I tried compile llama.cpp myself, add openblas and compile flag to optimize, it's slow though.

openmartin changed discussion status to closed Oct 21, 2025

Mungert

Owner Oct 21, 2025

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

thanks，you are right.
I tried compile llama.cpp myself, add openblas and compile flag to optimize, it's slow though.

if you have a cpu with avx512 support that can give a 30% performance boost.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment