SmolLM2 models
6 SmolLM2 models on Hugging Face, from 135M to 1.7B parameters. At the precision each one is published in, the smallest needs about 0.3 GB of VRAM (SmolLM2-135M, cheapest live fit: RTX 5060 Ti) and the largest about 3.8 GB (SmolLM2-1.7B, cheapest live fit: RTX 5060 Ti). The cheapest way to run SmolLM2-135M is $0.110/hr.
SmolLM2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SmolLM2-135M | 135M | BF16 | 0.3 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM2-135M-Instruct | 135M | BF16 | 0.3 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM2-360M | 362M | BF16 | 0.8 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM2-360M-Instruct | 362M | BF16 | 0.8 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM2-1.7B | 1.7B | BF16 | 3.8 GB | RTX 5060 Ti | $0.110/hr |
| SmolLM2-1.7B-Instruct | 1.7B | BF16 | 3.8 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.
