🔌
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 BiRNA-BERT?
Yes — here's how fast and up to what context, with real measured numbers.
BiRNA-BERT on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 73k | 349.4-416.4 t/s | ~31.2-37.2 (slow) |
| Q8 | yes | 75k | 698.8-832.8 t/s | ~62.4-74.4 (slow) |
| Q4 | yes | 75k | 1247.9-1487.2 t/s | ~111.4-132.8 (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 BiRNA-BERT?▶
Yes. At Q4 it generates ~1247.9-1487.2 tok/s and fits up to 75k context; beyond that it spills to SSD swap and slows to ~111.4-132.8 tok/s.
How much context fits?▶
At Q4, up to about 75k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.