🔌
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 Instinct MI455X run Phi-4-Multimodal?
Yes — here's how fast and up to what context, with real measured numbers.
Phi-4-Multimodal on the Instinct MI455X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2935k | 1102.5-1347.5 t/s | ~2.3-2.8 (slow) |
| Q8 | yes | 2978k | 2205-2695 t/s | ~4.5-5.5 (slow) |
| Q4 | yes | 2997k | 3937.5-4812.5 t/s | ~8-9.8 (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 Instinct MI455X run Phi-4-Multimodal?▶
Yes. At Q4 it generates ~3937.5-4812.5 tok/s and fits up to 2997k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8-9.8 tok/s.
How much context fits?▶
At Q4, up to about 2997k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.