Aya models
1 Aya model from Cohere on Hugging Face, from 8.0B to 8.0B parameters, published by Cohere in F16. The smallest official model, aya-expanse-8b, needs about 17.9 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official Aya size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| aya-expanse-8b | 8.0B | 17.9 GB | 9.0 GB | 4.5 GB | RTX A5000 | $0.176/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| aya-expanse-8b | 8.0B | F16 | 17.9 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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)
- Command R (2 models)