Llama 4 models
2 Llama 4 models on Hugging Face, from 108.6B to 401.6B parameters. At the precision each one is published in, the smallest needs about 243 GB of VRAM (Llama-4-Scout-17B-16E-Instruct, cheapest live fit: RTX A6000) and the largest about 449 GB (Llama-4-Maverick-17B-128E-Instruct-FP8, cheapest live fit: RTX PRO 6000). The cheapest way to run Llama-4-Scout-17B-16E-Instruct is $2.18/hr.
Llama 4 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Llama-4-Scout-17B-16E-Instruct | 108.6B | BF16 | 243 GB | RTX A6000 × 6 | $2.18/hr |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | 401.6B | F8_E4M3 | 449 GB | RTX PRO 6000 × 5 | $6.88/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 Meta
- Llama 3.2 (21 models)
- Llama 3.1 (42 models)
- Llama 3 (22 models)
- Llama 2 (11 models)
- Llama 3.3 (4 models)
- Code Llama (3 models)
- Llama (3 models)
- Llama Guard (4 models)
