UI TARS 72B SFT needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 23.7 GB (IQ1_M) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
UI TARS 72B SFT – a vision‑language model for GUI automation
UI TARS 72B SFT is a 72.7 billion‑parameter model built on the qwen2vl architecture. It supports vision and text, enabling end‑to‑end GUI interaction. The model is released under the apache‑2.0 license.
Good at
- Vision‑based GUI task automation
- End‑to‑end perception, reasoning, grounding
- Multimodal interaction
Limits
- No vision support in some quantizations
- Large VRAM requirement for full precision
- Requires llama.cpp for inference
Best for
- Automating desktop applications
- Building native GUI agents
- Testing UI workflows
Who it’s for. Developers and researchers needing a single VLM for GUI automation. The model is suitable for building agents that perceive screens, reason about actions, and execute them without external workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 23.7 GB | 26.9 GB | Too big | Get file → | |
| IQ2_XXS | 25.5 GB | 28.7 GB | Too big | Get file → | |
| IQ2_XS | 27.1 GB | 30.2 GB | Too big | Get file → | |
| IQ2_S | 27.9 GB | 31.1 GB | Too big | Get file → | |
| IQ2_M | 29.3 GB | 32.5 GB | Too big | Get file → | |
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| Q2_K_L | 31.0 GB | 34.2 GB | Too big | Get file → | |
| IQ3_XXS | 31.8 GB | 35.0 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| IQ3_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 39.7 GB | 42.9 GB | Too big | Get file → | |
| Q3_K_XL | 40.6 GB | 43.8 GB | Too big | Get file → | |
| IQ4_NL | 41.3 GB | 44.5 GB | Too big | Get file → | |
| Q4_0 | 41.4 GB | 44.6 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB | 47.1 GB | Too big | Get file → | |
| Q4_1 | 45.7 GB | 48.9 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB | 50.6 GB | Too big | Get file → | |
| Q5_K_S | 51.4 GB (2 parts) | 54.6 GB | Too big | Get file → | |
| Q5_K_M | 54.4 GB (2 parts) | 57.6 GB | Too big | Get file → | |
| Q6_K | 64.3 GB (2 parts) | 67.5 GB | Too big | Get file → | |
| Q8_0 | 77.3 GB (2 parts) | 80.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (23.74 GB file, 26.9 GB memory). For 16 GB VRAM, IQ2_S (27.94 GB file, 31.1 GB memory) is a good balance. For 32 GB VRAM, Q4_K_M (47.42 GB file, 50.6 GB memory) offers higher quality.
What GPU do you need for UI TARS 72B SFT?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ2_S (27.9 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which UI TARS 72B SFT quant should you choose?
Q4_K_M is the usual starting point for UI TARS 72B SFT: it balances file size and quality well. Here it is a 47.4 GB file.
The Q8_0 file is 77.3 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_M at 23.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about UI TARS 72B SFT
How much VRAM does UI TARS 72B SFT need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run UI TARS 72B SFT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of UI TARS 72B SFT GGUF?
It depends on the quant: IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB, Q2_K is 29.8 GB and 17 more.
What context length does UI TARS 72B SFT support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download UI TARS 72B SFT GGUF?
The files are on Hugging Face in the bartowski/UI-TARS-72B-SFT-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does UI TARS 72B SFT use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run UI TARS 72B SFT on 8 GB VRAM?
Use the IQ1_M quantization; it requires about 26.9 GB memory at 8k context, so it will not fit in 8 GB VRAM. A smaller quant like IQ2_XXS also needs more than 8 GB.
Does the model support vision?
Yes, the model has vision capability as detected in its abilities.
What license applies to this model?
The model is released under the apache-2.0 license.