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 SPIDER2?
Yes — here's how fast and up to what context, with real measured numbers.
SPIDER2 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1774k | 2620038.3-3252461.3 t/s | ~28324.7-35161.7 (slow) |
| Q8 | yes | 1774k | 5240076.6-6504922.6 t/s | ~56649.5-70323.5 (slow) |
| Q4 | yes | 1774k | 9357279.6-11615933.3 t/s | ~101159.8-125577.7 (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 SPIDER2?▶
Yes. At Q4 it generates ~9357279.6-11615933.3 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~101159.8-125577.7 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.