🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Instinct MI430X run GenSLM?
Yes — here's how fast and up to what context, with real measured numbers.
GenSLM on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1320k | 293.6-358.8 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 1415k | 587.2-717.6 t/s | ~1-1.2 (slow) |
| Q4 | yes | 1457k | 1048.5-1281.5 t/s | ~1.8-2.2 (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 GenSLM?▶
Yes. At Q4 it generates ~1048.5-1281.5 tok/s and fits up to 1457k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.8-2.2 tok/s.
How much context fits?▶
At Q4, up to about 1457k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.