🔌
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 MiniCPM-2.4B?
Yes — here's how fast and up to what context, with real measured numbers.
MiniCPM-2.4B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 576k | 199.6-242.6 t/s | ~5.3-6.5 (slow) |
| Q8 | yes | 614k | 399.3-485.2 t/s | ~10.6-12.9 (slow) |
| Q4 | yes | 630k | 713-866.5 t/s | ~19-23.1 (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 MiniCPM-2.4B?▶
Yes. At Q4 it generates ~713-866.5 tok/s and fits up to 630k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~19-23.1 tok/s.
How much context fits?▶
At Q4, up to about 630k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.