LongCat models
3 LongCat models on Hugging Face, from 69.1B to 561.9B parameters. At the precision each one is published in, the smallest needs about 77.2 GB of VRAM (LongCat-Flash-Lite-FP8, cheapest live fit: RTX PRO 6000) and the largest about 1256 GB (LongCat-Flash-Chat). The cheapest way to run LongCat-Flash-Lite-FP8 is $1.38/hr.
LongCat models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LongCat-Flash-Lite | 69.1B | BF16 | 154 GB | RTX A5000 × 7 | $1.23/hr |
| LongCat-Flash-Lite-FP8 | 69.1B | F8_E4M3 | 77.2 GB | RTX PRO 6000 | $1.38/hr |
| LongCat-Flash-Chat | 561.9B | BF16 | 1256 GB | No live fit | – |
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.
