Llama 2 models
11 Llama 2 models on Hugging Face, from 6.7B to 13.0B parameters. At the precision each one is published in, the smallest needs about 15.1 GB of VRAM (Llama-2-7b-chat-hf, cheapest live fit: V100) and the largest about 29.1 GB (llama2-13b-chat-hf, cheapest live fit: V100). The cheapest way to run Llama-2-7b-chat-hf is $0.088/hr.
Llama 2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Llama-2-7b-chat-hf | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| llama-2-7b | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| llama-2-7b-chat | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| Llama-2-7b-chat-hf | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| Llama-2-7b-hf | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| Llama-2-7b-chat-hf | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| Llama-2-7b-hf | 6.7B | F16 | 15.1 GB | V100 | $0.088/hr |
| HarmBench-Llama-2-13b-cls | 13.0B | BF16 | 29.1 GB | RTX 4080 Super | $0.338/hr |
| llama2-13b-chat-hf | 13.0B | F16 | 29.1 GB | V100 | $0.187/hr |
| Llama-2-13b-chat-hf | 13.0B | F16 | 29.1 GB | V100 | $0.187/hr |
| Llama-2-13b-hf | 13.0B | F16 | 29.1 GB | V100 | $0.187/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 3.3 (4 models)
- Code Llama (3 models)
- Llama (3 models)
- Llama Guard (4 models)
