Loading…
Loading…
Models / c4ai-command-a-03-2025
GPU memory needed (smallest version of each): c4ai-command-a-03-2025 ~111B about 268.8 GB. The cheapest runs on 8x Nvidia A100 from $4.26/h right now.
1 model (~111B) · ↓ 2.9K downloads a month · from $4.26/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-a-03-2025Licence to accept | vLLM | 222 GB | ~268.8 GB | $4.26/h 8x Nvidia A100 |
| command a reasoning 08 2025CohereLabs/command-a-reasoning-08-2025Licence to accept | vLLM | 222 GB | ~268.8 GB | $4.26/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").