---
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
tags:
- multimodal
- gui
- llama-cpp
- gguf-my-repo
library_name: transformers
base_model: bytedance-research/UI-TARS-72B-SFT
---

note: most qwen2 weights aren't divisible by 256, so this is really a q8/q5 quant.

# main-horse/UI-TARS-72B-SFT-Q4_K_M-GGUF
This model was converted to GGUF format from [`bytedance-research/UI-TARS-72B-SFT`](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) using llama.cpp.
Refer to the [original model card](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo main-horse/UI-TARS-72B-SFT-Q4_K_M-GGUF --hf-file UI-TARS-72B-SFT.Q4_K_M.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo main-horse/UI-TARS-72B-SFT-Q4_K_M-GGUF --hf-file UI-TARS-72B-SFT.Q4_K_M.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
```
Step 2: Build using CMake.
```
cmake -B build -DGGML_CUDA=ON -DGGML_CUDA_F16=1 -DGGML_CUDA_FA_ALL_QUANTS=1 -DCMAKE_CUDA_ARCHITECTURES=...
cmake --build build --config Release -j
```
Step 3: Run inference through the main binary.
```
./llama-server --hf-repo main-horse/UI-TARS-72B-SFT-Q4_K_M-GGUF --hf-file UI-TARS-72B-SFT.Q4_K_M.gguf -c 2048
```