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 AWD-LSTM-DOC (fin) (23M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (23M) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1773k | 46652.2-57913 t/s | ~504.3-626.1 (slow) |
| Q8 | yes | 1774k | 93304.3-115826.1 t/s | ~1008.7-1252.2 (slow) |
| Q4 | yes | 1774k | 166614.9-206832.3 t/s | ~1801.2-2236 (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 AWD-LSTM-DOC (fin) (23M)?▶
Yes. At Q4 it generates ~166614.9-206832.3 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1801.2-2236 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.