JetLM models
1 JetLM model on Hugging Face, from 2.0B to 2.0B parameters. The cheapest way to run SDAR-1.7B-Chat is $0.110/hr.
JetLM models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SDAR-1.7B-Chat | 2.0B | BF16 | 4.5 GB | RTX 3060 | $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.
