Command R models
2 Command R models on Hugging Face, from 8.0B to 35.0B parameters. At the precision each one is published in, the smallest needs about 17.9 GB of VRAM (c4ai-command-r7b-12-2024, cheapest live fit: RTX A5000) and the largest about 78.2 GB (c4ai-command-r-v01, cheapest live fit: A100). The cheapest way to run c4ai-command-r7b-12-2024 is $0.176/hr.
Command R models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| c4ai-command-r7b-12-2024 | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| c4ai-command-r-v01 | 35.0B | F16 | 78.2 GB | A100 | $1.31/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 Cohere
- CohereLabs (3 models)
