Llama models
3 Llama models on Hugging Face, from 134M to 6.7B parameters. At the precision each one is published in, the smallest needs about 0.6 GB of VRAM (AMD-Llama-135m, cheapest live fit: V100) and the largest about 15.1 GB (llama-7b, cheapest live fit: V100). The cheapest way to run AMD-Llama-135m is $0.088/hr.
Llama models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| AMD-Llama-135m | 134M | F32 | 0.6 GB | V100 | $0.088/hr |
| llama-160m | 162M | F32 | 0.7 GB | V100 | $0.088/hr |
| llama-7b | 6.7B | F16 | 15.1 GB | V100 | $0.088/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 Guard (4 models)
