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 DDPM-IP (CelebA)?
Yes — here's how fast and up to what context, with real measured numbers.
DDPM-IP (CelebA) on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6033k | 24879.7-30408.5 t/s | ~42.7-52.2 (slow) |
| Q8 | yes | 6037k | 49759.3-60816.9 t/s | ~85.4-104.4 (slow) |
| Q4 | yes | 6039k | 88855.9-108601.7 t/s | ~152.5-186.4 (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 DDPM-IP (CelebA)?▶
Yes. At Q4 it generates ~88855.9-108601.7 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~152.5-186.4 tok/s.
How much context fits?▶
At Q4, up to about 6039k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.