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 Selfish-RNN (SNT-ASGD) Stacked LSTMs?
Yes — here's how fast and up to what context, with real measured numbers.
Selfish-RNN (SNT-ASGD) Stacked LSTMs on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2672k | 115873-138095.2 t/s | ~579.4-690.5 (slow) |
| Q8 | yes | 2672k | 231746-276190.5 t/s | ~1158.7-1381 (slow) |
| Q4 | yes | 2672k | 413832.2-493197.3 t/s | ~2069.2-2466 (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 Selfish-RNN (SNT-ASGD) Stacked LSTMs?▶
Yes. At Q4 it generates ~413832.2-493197.3 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2069.2-2466 tok/s.
How much context fits?▶
At Q4, up to about 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.