SmolLM3 models
3 SmolLM3 models on Hugging Face, from 3.1B to 3.1B parameters. The cheapest way to run SmolLM3-3B is $0.110/hr.
SmolLM3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SmolLM3-3B | 3.1B | BF16 | 6.9 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM3-3B-Base | 3.1B | BF16 | 6.9 GB | RTX 5060 Ti | $0.110/hr |
| TwIL-LM3 | 3.1B | BF16 | 6.9 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.
