Loading…
Loading…
Models / c4ai-command-r-plus-08-2024
GPU memory needed (smallest version of each): c4ai-command-r-plus-08-2024 ~104B about 251.4 GB. The cheapest runs on 8x Nvidia A100 from $4.50/h right now.
1 model (~104B) · ↓ 120 downloads a month · from $4.50/h on 8x Nvidia A100 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalCohereLabs/c4ai-command-r-plus-08-2024Licence to accept | vLLM | 208 GB | ~251.4 GB | $4.50/h 8x Nvidia A100 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").