New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA B200 run Prithvi-EO-2.0 300M?
Yes — here's how fast and up to what context, with real measured numbers.
Prithvi-EO-2.0 300M on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2663k | 9733.3-11600 t/s | ~48.7-58 (slow) |
| Q8 | yes | 2668k | 19466.7-23200 t/s | ~97.3-116 (slow) |
| Q4 | yes | 2670k | 34761.9-41428.6 t/s | ~173.8-207.1 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA B200 run Prithvi-EO-2.0 300M?▶
Yes. At Q4 it generates ~34761.9-41428.6 tok/s and fits up to 2670k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~173.8-207.1 tok/s.
How much context fits?▶
At Q4, up to about 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.