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 MULAN?
Yes — here's how fast and up to what context, with real measured numbers.
MULAN on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6040k | 209700-256300 t/s | ~360-440 (slow) |
| Q8 | yes | 6041k | 419400-512600 t/s | ~720-880 (slow) |
| Q4 | yes | 6041k | 748928.6-915357.1 t/s | ~1285.7-1571.4 (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 MULAN?▶
Yes. At Q4 it generates ~748928.6-915357.1 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1285.7-1571.4 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.