Instructions to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Transformers:

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

pipe = pipeline("visual-question-answering", model="GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized 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 GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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 GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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 GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M

Use Docker

docker model run hf.co/GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M

LM Studio
Jan
Ollama
How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Ollama:
```
ollama run hf.co/GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
```
Unsloth Desktop

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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": "GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Docker Model Runner:
```
docker model run hf.co/GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M
```

Lemonade

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M

Run and chat with the model

lemonade run user.INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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 GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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 "GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized: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"

INFRL-Qwen2.5-VL-72B-Preview

Model Overview

INFRL-Qwen2.5-VL-72B-Preview improves visual reasoning upon Qwen2.5-VL-72B-Instruct model.
As of March 25th, 2025, INFRL-Qwen2.5-VL-72B-Preview is the best-performing open-sourced VL model on various visual reasoning benchmarks (MathVision,MathVista, MathVerse).

Evaluation

Models	MathVision (test)	MathVista (testmini)	MathVerse (testmini)
GPT4o	30.6	60	41.2
Gemini-2.0-Flash	41.3	70.1	50.6
Claude 3.5 Sonnet	33.5	67.7	47.8
QvQ-72B	35.9	71.4	48.6
InternVL2.5-78B	34.9	72.3	51.7
Qwen-VL-2.5-72B	38.1	74.8	57.18
INFRL-VL-Preview	41.9	77.8	58.84

We will release a code repository for VLM evaluation. It supports RL training with simple rule-based rewards, meanwhile aligning with LLM-Judge results.

Stay tuned!

Contributors

Supervisors

Wei Chu • Yuan Qi

VL Team

Haozhe Wang • Zuming Huang

RL Team

Haozhe Wang • Chao Qu • Long Li

Thanks

Thanks to Jiaran Hao, Liuyihan Song for supports in the RL infrastructure.

Citation

If you find our model useful, please consider citing:

@misc {INFRL_VL_Preview,
    author       = { {Wang, Haozhe and Huang, Zuming and Qu, Chao and Chu, Wei and Qi, Yuan} },
    title        = { INFRL-Qwen2.5-VL-72B-Preview },
    year         = 2025,
    url          = { https://huggingface.co/infly/INFRL-Qwen2.5-VL-72B-Preview},
    publisher    = { Hugging Face }
}

Downloads last month: 348

GGUF

Model size

73B params

Architecture

qwen2vl

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized

Base model

Qwen/Qwen2.5-VL-72B-Instruct

Quantized

(34)

this model

Collection including GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized

Qwen VLM based GGUFs

Collection

Qwen 2/2.5 VL models and finetunes GGUFs • 7 items • Updated May 17, 2025