🔌
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 NVIDIA RTX PRO 6000 Blackwell 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 NVIDIA RTX PRO 6000 Blackwell
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1221k | 192.4-229.3 t/s | ~4.3-5.1 (slow) |
| Q8 | yes | 1273k | 384.8-458.5 t/s | ~8.6-10.2 (slow) |
| Q4 | yes | 1296k | 687.1-818.8 t/s | ~15.3-18.3 (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.
→ All models on the NVIDIA RTX PRO 6000 Blackwell
→ Stable Diffusion XL (SDXL) specs
→ Other hardware
FAQ
Can the NVIDIA RTX PRO 6000 Blackwell run Stable Diffusion XL (SDXL)?▶
Yes. At Q4 it generates ~687.1-818.8 tok/s and fits up to 1296k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~15.3-18.3 tok/s.
How much context fits?▶
At Q4, up to about 1296k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.