maritaca-ai models
1 maritaca-ai model from maritaca-ai on Hugging Face, from 4.7B to 4.7B parameters, published by maritaca-ai in BF16, with a 256K-token context. The smallest official model, S5-nano, needs about 10.4 GB of VRAM at its published precision; the cheapest live fit is RTX 4070 at $0.154/hr.
Pick a size
One row per official maritaca-ai 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 |
|---|---|---|---|---|---|---|---|
| S5-nano | 4.7B | 10.4 GB | 5.2 GB | 2.6 GB | RTX 4070 | $0.154/hr | 1.0 GB |
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)
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.
