Llama 3.2 models
21 Llama 3.2 models on Hugging Face, from 506M to 88.6B parameters. At the precision each one is published in, the smallest needs about 1.1 GB of VRAM (Llama-3.2-0.5B-Instruct, cheapest live fit: RTX 5060 Ti) and the largest about 198 GB (Llama-3.2-90B-Vision-Instruct, cheapest live fit: RTX A6000). The cheapest way to run Llama-3.2-0.5B-Instruct is $0.110/hr.
Llama 3.2 models
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 3.1 (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)
