New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI440X run BERT-Large?
Yes — here's how fast and up to what context, with real measured numbers.
BERT-Large on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6031k | 18158.8-22194.1 t/s | ~37.1-45.3 (slow) |
| Q8 | yes | 6036k | 36317.6-44388.2 t/s | ~74.1-90.6 (slow) |
| Q4 | yes | 6039k | 64852.9-79264.7 t/s | ~132.4-161.8 (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 MI440X run BERT-Large?▶
Yes. At Q4 it generates ~64852.9-79264.7 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~132.4-161.8 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.