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 ALBERT?
Yes — here's how fast and up to what context, with real measured numbers.
ALBERT on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 27083.3-32916.7 t/s | ~722.2-877.8 (slow) |
| Q8 | yes | 651k | 54166.7-65833.3 t/s | ~1444.4-1755.6 (slow) |
| Q4 | yes | 651k | 96726.2-117559.5 t/s | ~2579.4-3134.9 (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 ALBERT?▶
Yes. At Q4 it generates ~96726.2-117559.5 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2579.4-3134.9 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.