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 Genie 2 (bio)?
Yes — here's how fast and up to what context, with real measured numbers.
Genie 2 (bio) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1774k | 68343.9-84840.8 t/s | ~738.9-917.2 (slow) |
| Q8 | yes | 1774k | 136687.9-169681.5 t/s | ~1477.7-1834.4 (slow) |
| Q4 | yes | 1774k | 244085.5-303002.7 t/s | ~2638.8-3275.7 (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 Genie 2 (bio)?▶
Yes. At Q4 it generates ~244085.5-303002.7 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2638.8-3275.7 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.