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 UniRep?
Yes — here's how fast and up to what context, with real measured numbers.
UniRep on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1773k | 58956-73186.8 t/s | ~637.4-791.2 (slow) |
| Q8 | yes | 1774k | 117912.1-146373.6 t/s | ~1274.7-1582.4 (slow) |
| Q4 | yes | 1774k | 210557.3-261381.5 t/s | ~2276.3-2825.7 (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 UniRep?▶
Yes. At Q4 it generates ~210557.3-261381.5 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2276.3-2825.7 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.