mistralai models
1 mistralai model from Mistral AI on Hugging Face, from 209M to 209M parameters, published by Mistral AI in F32. The smallest official model, Timestral-209M, needs about 0.9 GB of VRAM at its published precision; the cheapest live fit is P4 at $0.058/hr.
Pick a size
One row per official mistralai 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 |
|---|---|---|---|---|---|---|---|
| Timestral-209M | 209M | 0.9 GB | 0.2 GB | 0.1 GB | P4 | $0.058/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 |
|---|---|---|---|---|---|
| Timestral-209M | 209M | F32 | 0.9 GB | P4 | $0.058/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 Mistral AI
- Voxtral (1 models)
- Mistral 7B (7 models)
- Mistral Small (3 models)
- Mixtral (1 models)
