🔌
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 Ankh_large?
Yes — here's how fast and up to what context, with real measured numbers.
Ankh_large on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 593k | 256.6-311.8 t/s | ~6.8-8.3 (slow) |
| Q8 | yes | 622k | 513.2-623.7 t/s | ~13.7-16.6 (slow) |
| Q4 | yes | 635k | 916.4-1113.7 t/s | ~24.4-29.7 (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 Ankh_large?▶
Yes. At Q4 it generates ~916.4-1113.7 tok/s and fits up to 635k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~24.4-29.7 tok/s.
How much context fits?▶
At Q4, up to about 635k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.