🔌
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 (LDM-KL-8-G)?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Diffusion (LDM-KL-8-G) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1730k | 740-918.6 t/s | ~8-9.9 (slow) |
| Q8 | yes | 1752k | 1480-1837.2 t/s | ~16-19.9 (slow) |
| Q4 | yes | 1762k | 2642.9-3280.8 t/s | ~28.6-35.5 (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 (LDM-KL-8-G)?▶
Yes. At Q4 it generates ~2642.9-3280.8 tok/s and fits up to 1762k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~28.6-35.5 tok/s.
How much context fits?▶
At Q4, up to about 1762k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.