🔌
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 GePpeTto?
Yes — here's how fast and up to what context, with real measured numbers.
GePpeTto on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 647k | 4166.7-5064.1 t/s | ~111.1-135 (slow) |
| Q8 | yes | 649k | 8333.3-10128.2 t/s | ~222.2-270.1 (slow) |
| Q4 | yes | 650k | 14881-18086.1 t/s | ~396.8-482.3 (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 GePpeTto?▶
Yes. At Q4 it generates ~14881-18086.1 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~396.8-482.3 tok/s.
How much context fits?▶
At Q4, up to about 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.