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 CodeT5-large?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-large on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6018k | 9531.8-11650 t/s | ~16.4-20 (slow) |
| Q8 | yes | 6030k | 19063.6-23300 t/s | ~32.7-40 (slow) |
| Q4 | yes | 6035k | 34042.2-41607.1 t/s | ~58.4-71.4 (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 CodeT5-large?▶
Yes. At Q4 it generates ~34042.2-41607.1 tok/s and fits up to 6035k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~58.4-71.4 tok/s.
How much context fits?▶
At Q4, up to about 6035k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.