Typhoon models
6 Typhoon models on Hugging Face, from 2.1B to 30.5B parameters. At the precision each one is published in, the smallest needs about 4.8 GB of VRAM (typhoon-ocr1.5-2b, cheapest live fit: RTX 5060 Ti) and the largest about 68.2 GB (typhoon2.5-qwen3-30b-a3b, cheapest live fit: A100). The cheapest way to run typhoon-ocr1.5-2b is $0.110/hr.
Typhoon models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| typhoon-ocr1.5-2b | 2.1B | BF16 | 4.8 GB | RTX 5060 Ti | $0.110/hr |
| typhoon-ocr-3b | 3.8B | BF16 | 8.4 GB | RTX 5060 Ti | $0.110/hr |
| typhoon2.5-qwen3-4b | 4.0B | BF16 | 9.0 GB | RTX 5060 Ti | $0.110/hr |
| llama-3-typhoon-v1.5-8b-instruct | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| llama3.1-typhoon2-8b-instruct | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| typhoon2.5-qwen3-30b-a3b | 30.5B | BF16 | 68.2 GB | A100 | $1.31/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.
