🔌
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 Gemma 3 270M?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 3 270M on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 643k | 1805.6-2194.4 t/s | ~48.1-58.5 (slow) |
| Q8 | yes | 647k | 3611.1-4388.9 t/s | ~96.3-117 (slow) |
| Q4 | yes | 649k | 6448.4-7837.3 t/s | ~172-209 (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 Gemma 3 270M?▶
Yes. At Q4 it generates ~6448.4-7837.3 tok/s and fits up to 649k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~172-209 tok/s.
How much context fits?▶
At Q4, up to about 649k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.