Nemotron Cascade models
1 Nemotron Cascade model from NVIDIA on Hugging Face, from 31.6B to 31.6B parameters, published by NVIDIA in BF16, with a 256K-token context. The smallest official model, Nemotron-Cascade-2-30B-A3B, needs about 70.6 GB of VRAM at its published precision; the cheapest live fit is A100 at $1.21/hr.
Part of the Nemotron series
Pick a size
One row per official Nemotron Cascade 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 |
|---|---|---|---|---|---|---|---|
| Nemotron-Cascade-2-30B-A3B | 31.6B | 70.6 GB | 35.3 GB | 17.6 GB | A100 | $1.21/hr | 0.19 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Nemotron-Cascade-2-30B-A3B | 31.6B | BF16 | 70.6 GB | A100 | $1.21/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 NVIDIA
- Parakeet (7 models)
- Nemotron 3 (17 models)
- Cosmos (6 models)
- Nemotron Nano (4 models)
- Nemotron Labs (4 models)
- Nemotron-H (3 models)
