🔌
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 GeForce RTX 4070 Ti Super run Stable Diffusion 3.5 Medium?
Yes — here's how fast and up to what context, with real measured numbers.
Stable Diffusion 3.5 Medium on the NVIDIA GeForce RTX 4070 Ti Super
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 125k | 98.1-116.9 t/s | ~5.8-7 (slow) |
| Q8 | yes | 164k | 196.2-233.9 t/s | ~11.7-13.9 (slow) |
| Q4 | yes | 180k | 350.4-417.6 t/s | ~20.9-24.9 (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 NVIDIA GeForce RTX 4070 Ti Super
→ Stable Diffusion 3.5 Medium specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 4070 Ti Super run Stable Diffusion 3.5 Medium?▶
Yes. At Q4 it generates ~350.4-417.6 tok/s and fits up to 180k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~20.9-24.9 tok/s.
How much context fits?▶
At Q4, up to about 180k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.