🔌
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 ProGen2-xlarge?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-xlarge on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 228k | 76.2-92.6 t/s | ~2-2.5 (slow) |
| Q8 | yes | 277k | 152.3-185.2 t/s | ~4.1-4.9 (slow) |
| Q4 | yes | 298k | 272-330.6 t/s | ~7.3-8.8 (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 ProGen2-xlarge?▶
Yes. At Q4 it generates ~272-330.6 tok/s and fits up to 298k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.3-8.8 tok/s.
How much context fits?▶
At Q4, up to about 298k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.