New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI430X run StyleGAN3-T?
Yes — here's how fast and up to what context, with real measured numbers.
StyleGAN3-T on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6041k | 3291255.6-4022645.7 t/s | ~5650.2-6905.8 (slow) |
| Q8 | yes | 6042k | 6582511.2-8045291.5 t/s | ~11300.4-13811.7 (slow) |
| Q4 | yes | 6042k | 11754484.3-14366591.9 t/s | ~20179.4-24663.7 (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 Instinct MI430X run StyleGAN3-T?▶
Yes. At Q4 it generates ~11754484.3-14366591.9 tok/s and fits up to 6042k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~20179.4-24663.7 tok/s.
How much context fits?▶
At Q4, up to about 6042k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.