Llama 3 models
22 Llama 3 models on Hugging Face, from 8.0B to 70.6B parameters. At the precision each one is published in, the smallest needs about 9.0 GB of VRAM (Meta-Llama-3-8B-Instruct-nonuniform-test, cheapest live fit: RTX 5060 Ti) and the largest about 158 GB (Meta-Llama-3-70B, cheapest live fit: RTX A5000). The cheapest way to run Meta-Llama-3-8B-Instruct-nonuniform-test is $0.110/hr.
Llama 3 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 3.2 (21 models)
- Llama 3.1 (42 models)
- Llama 2 (11 models)
- Llama 3.3 (4 models)
- Code Llama (3 models)
- Llama (3 models)
- Llama Guard (4 models)
