🔌
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 AMD Radeon Pro W7900 48GB 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 AMD Radeon Pro W7900 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 607k | 187.7-229.4 t/s | ~8.7-10.6 (slow) |
| Q8 | yes | 629k | 375.4-458.8 t/s | ~17.4-21.2 (slow) |
| Q4 | yes | 639k | 670.3-819.3 t/s | ~31-37.9 (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 AMD Radeon Pro W7900 48GB
→ Stable Diffusion (LDM-KL-8-G) specs
→ Other hardware
FAQ
Can the AMD Radeon Pro W7900 48GB run Stable Diffusion (LDM-KL-8-G)?▶
Yes. At Q4 it generates ~670.3-819.3 tok/s and fits up to 639k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~31-37.9 tok/s.
How much context fits?▶
At Q4, up to about 639k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.