🔌
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 Phi-4-Multimodal?
Yes — here's how fast and up to what context, with real measured numbers.
Phi-4-Multimodal on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 240k | 87.1-105.8 t/s | ~2.3-2.8 (slow) |
| Q8 | yes | 283k | 174.1-211.6 t/s | ~4.6-5.6 (slow) |
| Q4 | yes | 302k | 310.9-377.9 t/s | ~8.3-10.1 (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 Phi-4-Multimodal?▶
Yes. At Q4 it generates ~310.9-377.9 tok/s and fits up to 302k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.3-10.1 tok/s.
How much context fits?▶
At Q4, up to about 302k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.