Will this model run on your hardware?
Can I run ByteDance: UI-TARS 7B locally?
- 8.3B parameters
- context up to 125K
- licence: apache-2.0
- Weights: ByteDance-Seed/UI-TARS-1.5-7B · GGUF: mradermacher/UI-TARS-1.5-7B-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 8.1 GB |
| Q6_K | 6.3 GB |
| Q5_K_M | 5.4 GB |
| Q4_K_M | 4.7 GB |
| Q3_K_M | 3.8 GB |
| Q2_K | 3.0 GB |
Run it locally
ollama run hf.co/mradermacher/UI-TARS-1.5-7B-GGUF:Q4_K_M
llama serve -hf mradermacher/UI-TARS-1.5-7B-GGUF:Q4_K_M
LM Studio: open mradermacher/UI-TARS-1.5-7B-GGUF