New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Can the Intel Gaudi 3 run Prithvi WxC?
Yes โ here's how fast and up to what context, with real measured numbers.
Prithvi WxC on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1704k | 466.5-579.1 t/s | ~5-6.3 (slow) |
| Q8 | yes | 1739k | 933-1158.3 t/s | ~10.1-12.5 (slow) |
| Q4 | yes | 1754k | 1666.1-2068.3 t/s | ~18-22.4 (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 Prithvi WxC?โถ
Yes. At Q4 it generates ~1666.1-2068.3 tok/s and fits up to 1754k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~18-22.4 tok/s.
How much context fits?โถ
At Q4, up to about 1754k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.