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 BigGAN-deep 512x512?
Yes — here's how fast and up to what context, with real measured numbers.
BigGAN-deep 512x512 on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6038k | 65127.2-79600 t/s | ~111.8-136.7 (slow) |
| Q8 | yes | 6040k | 130254.5-159199.9 t/s | ~223.6-273.3 (slow) |
| Q4 | yes | 6041k | 232597.3-284285.6 t/s | ~399.3-488 (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 BigGAN-deep 512x512?▶
Yes. At Q4 it generates ~232597.3-284285.6 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~399.3-488 tok/s.
How much context fits?▶
At Q4, up to about 6041k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.