🔌
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-450M?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-450M on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 637k | 1083.3-1316.7 t/s | ~28.9-35.1 (slow) |
| Q8 | yes | 644k | 2166.7-2633.3 t/s | ~57.8-70.2 (slow) |
| Q4 | yes | 647k | 3869-4702.4 t/s | ~103.2-125.4 (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-450M?▶
Yes. At Q4 it generates ~3869-4702.4 tok/s and fits up to 647k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~103.2-125.4 tok/s.
How much context fits?▶
At Q4, up to about 647k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.