🔌
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 A100 SXM4 80GB run ProtBERT-BFD?
Yes — here's how fast and up to what context, with real measured numbers.
ProtBERT-BFD on the NVIDIA A100 SXM4 80GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1087k | 1772-2111.8 t/s | ~34.8-41.4 (slow) |
| Q8 | yes | 1094k | 3544-4223.6 t/s | ~69.5-82.9 (slow) |
| Q4 | yes | 1097k | 6328.5-7542.2 t/s | ~124.1-148 (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 A100 SXM4 80GB run ProtBERT-BFD?▶
Yes. At Q4 it generates ~6328.5-7542.2 tok/s and fits up to 1097k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~124.1-148 tok/s.
How much context fits?▶
At Q4, up to about 1097k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.