StableLM models
3 StableLM models on Hugging Face, from 1.6B to 2.8B parameters. At the precision each one is published in, the smallest needs about 3.7 GB of VRAM (stablelm-2-zephyr-1_6b, cheapest live fit: V100) and the largest about 6.2 GB (stablelm-3b-4e1t, cheapest live fit: RTX 5060 Ti). The cheapest way to run stablelm-2-zephyr-1_6b is $0.088/hr.
StableLM models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| stablelm-2-zephyr-1_6b | 1.6B | F16 | 3.7 GB | V100 | $0.088/hr |
| stablelm-3b-4e1t | 2.8B | BF16 | 6.2 GB | RTX 5060 Ti | $0.110/hr |
| stablelm-zephyr-3b | 2.8B | BF16 | 6.2 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.
More from Stability AI
- Stable Diffusion XL (33 models)
- Stable Diffusion (9 models)
- Stable Diffusion 3 (3 models)
- stabilityai (3 models)
