Bytedance research.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 6 quants, from 29.8 GB (Q2_K) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Bytedance research.UI TARS 72B SFT is a 72.7B-parameter Tars model in GGUF format, quantized by DevQuasar. Its trained context length is 32K tokens. The repository has 6 quant files, from 29.8 GB (Q2_K) to 77.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB (4 parts) | 50.6 GB | Too big | Get file → | |
| Q5_K_M | 54.4 GB (4 parts) | 57.6 GB | Too big | Get file → | |
| Q6_K | 64.3 GB (5 parts) | 67.5 GB | Too big | Get file → | |
| Q8_0 | 77.3 GB (6 parts) | 80.4 GB | Too big | Get file → |
What GPU do you need for Bytedance research.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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q3_K_M (37.7 GB file, about 40.9 GB in use).
Which Bytedance research.UI TARS 72B SFT quant should you choose?
Q4_K_M is the usual starting point for Bytedance research.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 Q2_K at 29.8 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 Bytedance research.UI TARS 72B SFT
How much VRAM does Bytedance research.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 Bytedance research.UI TARS 72B SFT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 33.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Bytedance research.UI TARS 72B SFT GGUF?
It depends on the quant: Q2_K is 29.8 GB, Q3_K_M is 37.7 GB, Q4_K_M is 47.4 GB, Q5_K_M is 54.4 GB, Q6_K is 64.3 GB, Q8_0 is 77.3 GB.
What context length does Bytedance research.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 Bytedance research.UI TARS 72B SFT GGUF?
The files are on Hugging Face in the DevQuasar/bytedance-research.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 Bytedance research.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.