LLaDA models
5 LLaDA models on Hugging Face, from 8.0B to 16.3B parameters. At the precision each one is published in, the smallest needs about 17.9 GB of VRAM (LLaDA-1.5, cheapest live fit: RTX A5000) and the largest about 36.3 GB (LLaDA2.0-mini, cheapest live fit: RTX A6000). The cheapest way to run LLaDA-1.5 is $0.176/hr.
LLaDA models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LLaDA-1.5 | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| LLaDA-8B-Base | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| LLaDA-8B-Instruct | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| LLaDA2.0-mini | 16.3B | BF16 | 36.3 GB | RTX A6000 | $0.363/hr |
| LLaDA2.1-mini | 16.3B | BF16 | 36.3 GB | RTX A6000 | $0.363/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.
More from inclusionAI
- Ling (3 models)
