New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the AMD Instinct MI300X 192GB run LUKE?
Yes — here's how fast and up to what context, with real measured numbers.
LUKE on the AMD Instinct MI300X 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2658k | 3456.5-4224.6 t/s | ~26.1-31.9 (slow) |
| Q8 | yes | 2665k | 6913-8449.3 t/s | ~52.2-63.8 (slow) |
| Q4 | yes | 2668k | 12344.7-15088 t/s | ~93.2-113.9 (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 AMD Instinct MI300X 192GB run LUKE?▶
Yes. At Q4 it generates ~12344.7-15088 tok/s and fits up to 2668k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~93.2-113.9 tok/s.
How much context fits?▶
At Q4, up to about 2668k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.