🔌
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 Stable Diffusion XL (SDXL)?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Diffusion XL (SDXL) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1670k | 315.6-391.8 t/s | ~3.4-4.2 (slow) |
| Q8 | yes | 1722k | 631.2-783.5 t/s | ~6.8-8.5 (slow) |
| Q4 | yes | 1745k | 1127.1-1399.2 t/s | ~12.2-15.1 (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 Stable Diffusion XL (SDXL)?▶
Yes. At Q4 it generates ~1127.1-1399.2 tok/s and fits up to 1745k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~12.2-15.1 tok/s.
How much context fits?▶
At Q4, up to about 1745k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.