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 MI325X run Tranception?
Yes — here's how fast and up to what context, with real measured numbers.
Tranception on the AMD Instinct MI325X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 3549k | 2700-3300 t/s | ~18-22 (slow) |
| Q8 | yes | 3560k | 5400-6600 t/s | ~36-44 (slow) |
| Q4 | yes | 3565k | 9642.9-11785.7 t/s | ~64.3-78.6 (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 MI325X run Tranception?▶
Yes. At Q4 it generates ~9642.9-11785.7 tok/s and fits up to 3565k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~64.3-78.6 tok/s.
How much context fits?▶
At Q4, up to about 3565k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.