New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Intel Gaudi 3 run BIDAF?
Yes — here's how fast and up to what context, with real measured numbers.
BIDAF on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1774k | 412692.3-512307.7 t/s | ~4461.5-5538.5 (slow) |
| Q8 | yes | 1774k | 825384.6-1024615.4 t/s | ~8923.1-11076.9 (slow) |
| Q4 | yes | 1774k | 1473901.1-1829670.3 t/s | ~15934.1-19780.2 (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 Intel Gaudi 3 run BIDAF?▶
Yes. At Q4 it generates ~1473901.1-1829670.3 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~15934.1-19780.2 tok/s.
How much context fits?▶
At Q4, up to about 1774k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.