🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA RTX PRO 6000 Blackwell run ESM1b?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1b on the NVIDIA RTX PRO 6000 Blackwell
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1305k | 1002.6-1194.8 t/s | ~22.4-26.7 (slow) |
| Q8 | yes | 1315k | 2005.2-2389.7 t/s | ~44.8-53.3 (slow) |
| Q4 | yes | 1319k | 3580.6-4267.3 t/s | ~79.9-95.3 (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 RTX PRO 6000 Blackwell run ESM1b?▶
Yes. At Q4 it generates ~3580.6-4267.3 tok/s and fits up to 1319k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~79.9-95.3 tok/s.
How much context fits?▶
At Q4, up to about 1319k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.