🔌
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 Rita-XLarge?
Yes — here's how fast and up to what context, with real measured numbers.
Rita-XLarge on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 40k | 34.1-40.6 t/s | ~3-3.6 (slow) |
| Q8 | yes | 58k | 68.1-81.2 t/s | ~6.1-7.3 (slow) |
| Q4 | yes | 66k | 121.7-145 t/s | ~10.9-12.9 (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 Rita-XLarge?▶
Yes. At Q4 it generates ~121.7-145 tok/s and fits up to 66k context; beyond that it spills to SSD swap and slows to ~10.9-12.9 tok/s.
How much context fits?▶
At Q4, up to about 66k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.