🔌
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-7.1B?
Yes — here's how fast and up to what context, with real measured numbers.
BLOOM-7.1B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 218k | 69-83.8 t/s | ~1.8-2.2 (slow) |
| Q8 | yes | 272k | 137.9-167.6 t/s | ~3.7-4.5 (slow) |
| Q4 | yes | 295k | 246.3-299.3 t/s | ~6.6-8 (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-7.1B?▶
Yes. At Q4 it generates ~246.3-299.3 tok/s and fits up to 295k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.6-8 tok/s.
How much context fits?▶
At Q4, up to about 295k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.