llm-jp models
2 llm-jp models on Hugging Face, from 152M to 33.2B parameters. At the precision each one is published in, the smallest needs about 0.3 GB of VRAM (llm-jp-3-150m, cheapest live fit: RTX 3060) and the largest about 74.3 GB (llm-jp-4-33b-thinking, cheapest live fit: A100). The cheapest way to run llm-jp-3-150m is $0.110/hr.
llm-jp models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| llm-jp-3-150m | 152M | BF16 | 0.3 GB | RTX 3060 | $0.110/hr |
| llm-jp-4-33b-thinking | 33.2B | BF16 | 74.3 GB | A100 | $1.31/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.
