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 ERNIE-GEN (large)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-GEN (large) on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6031k | 21586.8-26383.8 t/s | ~37.1-45.3 (slow) |
| Q8 | yes | 6036k | 43173.5-52767.6 t/s | ~74.1-90.6 (slow) |
| Q4 | yes | 6039k | 77095.6-94227.9 t/s | ~132.4-161.8 (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 MI430X run ERNIE-GEN (large)?▶
Yes. At Q4 it generates ~77095.6-94227.9 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~132.4-161.8 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.