🔌
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 BLOOM-560M?
Yes — here's how fast and up to what context, with real measured numbers.
BLOOM-560M on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 634k | 870.5-1058 t/s | ~23.2-28.2 (slow) |
| Q8 | yes | 642k | 1741.1-2116.1 t/s | ~46.4-56.4 (slow) |
| Q4 | yes | 646k | 3109.1-3778.7 t/s | ~82.9-100.8 (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 BLOOM-560M?▶
Yes. At Q4 it generates ~3109.1-3778.7 tok/s and fits up to 646k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~82.9-100.8 tok/s.
How much context fits?▶
At Q4, up to about 646k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.