New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the FuriosaAI RNGD run ProBERTa?
Yes — here's how fast and up to what context, with real measured numbers.
ProBERTa on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 11079.5-13465.9 t/s | ~295.5-359.1 (slow) |
| Q8 | yes | 650k | 22159.1-26931.8 t/s | ~590.9-718.2 (slow) |
| Q4 | yes | 651k | 39569.8-48092.5 t/s | ~1055.2-1282.5 (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 ProBERTa?▶
Yes. At Q4 it generates ~39569.8-48092.5 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1055.2-1282.5 tok/s.
How much context fits?▶
At Q4, up to about 651k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.