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 CamemBERT?
Yes — here's how fast and up to what context, with real measured numbers.
CamemBERT on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6031k | 18429.9-22525.4 t/s | ~37.6-46 (slow) |
| Q8 | yes | 6036k | 36859.7-45050.7 t/s | ~75.2-91.9 (slow) |
| Q4 | yes | 6039k | 65820.9-80447.8 t/s | ~134.3-164.2 (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 CamemBERT?▶
Yes. At Q4 it generates ~65820.9-80447.8 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~134.3-164.2 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.