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 GemNet-T (OC20)?
Yes — here's how fast and up to what context, with real measured numbers.
GemNet-T (OC20) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2672k | 1536842.1-1831578.9 t/s | ~7684.2-9157.9 (slow) |
| Q8 | yes | 2672k | 3073684.2-3663157.9 t/s | ~15368.4-18315.8 (slow) |
| Q4 | yes | 2672k | 5488721.8-6541353.4 t/s | ~27443.6-32706.8 (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 GemNet-T (OC20)?▶
Yes. At Q4 it generates ~5488721.8-6541353.4 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~27443.6-32706.8 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.