🔌
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 SmolLM-1.7B?
Yes — here's how fast and up to what context, with real measured numbers.
SmolLM-1.7B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 599k | 285.1-346.5 t/s | ~7.6-9.2 (slow) |
| Q8 | yes | 625k | 570.2-693 t/s | ~15.2-18.5 (slow) |
| Q4 | yes | 636k | 1018.2-1237.5 t/s | ~27.2-33 (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 SmolLM-1.7B?▶
Yes. At Q4 it generates ~1018.2-1237.5 tok/s and fits up to 636k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~27.2-33 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.