🔌
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 2050 run DDPM-IP (CelebA)?
Yes — here's how fast and up to what context, with real measured numbers.
DDPM-IP (CelebA) on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 67k | 138.6-165.2 t/s | ~12.4-14.7 (slow) |
| Q8 | yes | 72k | 277.2-330.3 t/s | ~24.7-29.5 (slow) |
| Q4 | yes | 74k | 494.9-589.8 t/s | ~44.2-52.7 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA GeForce RTX 2050 run DDPM-IP (CelebA)?▶
Yes. At Q4 it generates ~494.9-589.8 tok/s and fits up to 74k context; beyond that it spills to SSD swap and slows to ~44.2-52.7 tok/s.
How much context fits?▶
At Q4, up to about 74k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.