🔌
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 Ling-mini-base-2.0-20T?
Yes — here's how fast and up to what context, with real measured numbers.
Ling-mini-base-2.0-20T on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 41k | 30.5-37 t/s | ~0.8-1 (slow) |
| Q8 | yes | 102k | 60.9-74.1 t/s | ~1.6-2 (slow) |
| Q4 | yes | 129k | 108.8-132.3 t/s | ~2.9-3.5 (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 Ling-mini-base-2.0-20T?▶
Yes. At Q4 it generates ~108.8-132.3 tok/s and fits up to 129k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.9-3.5 tok/s.
How much context fits?▶
At Q4, up to about 129k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.