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 Pythia-160m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-160m on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6037k | 45871.9-56065.6 t/s | ~78.8-96.3 (slow) |
| Q8 | yes | 6039k | 91743.8-112131.3 t/s | ~157.5-192.5 (slow) |
| Q4 | yes | 6040k | 163828.1-200234.4 t/s | ~281.3-343.8 (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 Pythia-160m?▶
Yes. At Q4 it generates ~163828.1-200234.4 tok/s and fits up to 6040k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~281.3-343.8 tok/s.
How much context fits?▶
At Q4, up to about 6040k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.