ai4bharat models
1 ai4bharat model from ai4bharat on Hugging Face, from 351M to 351M parameters, published by ai4bharat in F32. The smallest official model, IndicF5, needs about 1.6 GB of VRAM at its published precision; the cheapest live fit is V100 at $0.077/hr.
Pick a size
One row per official ai4bharat 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 |
|---|---|---|---|---|---|---|---|
| IndicF5 | 351M | 1.6 GB | 0.4 GB | 0.2 GB | V100 | $0.077/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)
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.