New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI455X run GPT-2 (355M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (355M) on the Instinct MI455X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6031k | 17391.5-21256.3 t/s | ~35.5-43.4 (slow) |
| Q8 | yes | 6036k | 34783.1-42512.7 t/s | ~71-86.8 (slow) |
| Q4 | yes | 6039k | 62112.7-75915.5 t/s | ~126.8-154.9 (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 Instinct MI455X run GPT-2 (355M)?▶
Yes. At Q4 it generates ~62112.7-75915.5 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~126.8-154.9 tok/s.
How much context fits?▶
At Q4, up to about 6039k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.