🔌
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 OpenELM-1.1B?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-1.1B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 618k | 451.4-548.6 t/s | ~12-14.6 (slow) |
| Q8 | yes | 634k | 902.8-1097.2 t/s | ~24.1-29.3 (slow) |
| Q4 | yes | 642k | 1612.1-1959.3 t/s | ~43-52.2 (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 OpenELM-1.1B?▶
Yes. At Q4 it generates ~1612.1-1959.3 tok/s and fits up to 642k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~43-52.2 tok/s.
How much context fits?▶
At Q4, up to about 642k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.