Falcon-H1 models
4 Falcon-H1 models on Hugging Face, from 521M to 7.6B parameters. At the precision each one is published in, the smallest needs about 1.2 GB of VRAM (Falcon-H1-0.5B-Base, cheapest live fit: RTX 5060 Ti) and the largest about 17.0 GB (Falcon-H1-7B-Instruct, cheapest live fit: RTX A5000). The cheapest way to run Falcon-H1-0.5B-Base is $0.110/hr.
Falcon-H1 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Falcon-H1-0.5B-Base | 521M | BF16 | 1.2 GB | RTX 5060 Ti | $0.110/hr |
| Falcon-H1-0.5B-Instruct | 521M | BF16 | 1.2 GB | RTX 5060 Ti | $0.110/hr |
| Falcon-H1-1.5B-Deep-Instruct | 1.6B | BF16 | 3.5 GB | RTX 5060 Ti | $0.110/hr |
| Falcon-H1-7B-Instruct | 7.6B | BF16 | 17.0 GB | RTX A5000 | $0.176/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.
