🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Intel Gaudi 3 run Unified-IO (XL)?
Yes — here's how fast and up to what context, with real measured numbers.
Unified-IO (XL) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1685k | 366.8-455.4 t/s | ~4-4.9 (slow) |
| Q8 | yes | 1729k | 733.7-910.8 t/s | ~7.9-9.8 (slow) |
| Q4 | yes | 1749k | 1310.1-1626.4 t/s | ~14.2-17.6 (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 Unified-IO (XL)?▶
Yes. At Q4 it generates ~1310.1-1626.4 tok/s and fits up to 1749k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~14.2-17.6 tok/s.
How much context fits?▶
At Q4, up to about 1749k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.