🔌
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 SantaCoder?
Yes — here's how fast and up to what context, with real measured numbers.
SantaCoder on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 617k | 443.2-538.6 t/s | ~11.8-14.4 (slow) |
| Q8 | yes | 634k | 886.4-1077.3 t/s | ~23.6-28.7 (slow) |
| Q4 | yes | 642k | 1582.8-1923.7 t/s | ~42.2-51.3 (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 SantaCoder?▶
Yes. At Q4 it generates ~1582.8-1923.7 tok/s and fits up to 642k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~42.2-51.3 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.