🔌
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 KoGPT?
Yes — here's how fast and up to what context, with real measured numbers.
KoGPT on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 231k | 79.1-96.1 t/s | ~2.1-2.6 (slow) |
| Q8 | yes | 278k | 158.1-192.2 t/s | ~4.2-5.1 (slow) |
| Q4 | yes | 299k | 282.3-343.2 t/s | ~7.5-9.2 (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 KoGPT?▶
Yes. At Q4 it generates ~282.3-343.2 tok/s and fits up to 299k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.5-9.2 tok/s.
How much context fits?▶
At Q4, up to about 299k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.