🔌
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 Polyglot-Ko-12.8B?
Yes — here's how fast and up to what context, with real measured numbers.
Polyglot-Ko-12.8B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 103k | 37.8-45.9 t/s | ~1-1.2 (slow) |
| Q8 | yes | 182k | 75.6-91.9 t/s | ~2-2.4 (slow) |
| Q4 | yes | 216k | 135-164.1 t/s | ~3.6-4.4 (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 Polyglot-Ko-12.8B?▶
Yes. At Q4 it generates ~135-164.1 tok/s and fits up to 216k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.6-4.4 tok/s.
How much context fits?▶
At Q4, up to about 216k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.