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 RNA-FrameFlow?
Yes — here's how fast and up to what context, with real measured numbers.
RNA-FrameFlow on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6041k | 436875-533958.3 t/s | ~750-916.7 (slow) |
| Q8 | yes | 6041k | 873750-1067916.7 t/s | ~1500-1833.3 (slow) |
| Q4 | yes | 6041k | 1560267.9-1906994 t/s | ~2678.6-3273.8 (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 RNA-FrameFlow?▶
Yes. At Q4 it generates ~1560267.9-1906994 tok/s and fits up to 6041k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2678.6-3273.8 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.