🔌
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 FuriosaAI RNGD run BERT-Large?
Yes — here's how fast and up to what context, with real measured numbers.
BERT-Large on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 641k | 1433.8-1742.6 t/s | ~38.2-46.5 (slow) |
| Q8 | yes | 646k | 2867.6-3485.3 t/s | ~76.5-92.9 (slow) |
| Q4 | yes | 648k | 5120.8-6223.7 t/s | ~136.6-166 (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 FuriosaAI RNGD run BERT-Large?▶
Yes. At Q4 it generates ~5120.8-6223.7 tok/s and fits up to 648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~136.6-166 tok/s.
How much context fits?▶
At Q4, up to about 648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.