Nanbeige models
3 Nanbeige models on Hugging Face, from 848M to 4.2B parameters. At the precision each one is published in, the smallest needs about 1.9 GB of VRAM (Nanbeige4.2-3B-DSpark, cheapest live fit: RTX 5060 Ti) and the largest about 9.3 GB (Nanbeige4.2-3B, cheapest live fit: RTX 5060 Ti). The cheapest way to run Nanbeige4.2-3B-DSpark is $0.110/hr.
Nanbeige models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Nanbeige4.2-3B-DSpark | 848M | BF16 | 1.9 GB | RTX 5060 Ti | $0.110/hr |
| Nanbeige4.1-3B | 3.9B | BF16 | 8.8 GB | RTX 5060 Ti | $0.110/hr |
| Nanbeige4.2-3B | 4.2B | BF16 | 9.3 GB | RTX 5060 Ti | $0.110/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
