🔌
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 ERNIE-Doc (247M)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc (247M) on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 69k | 165.5-197.2 t/s | ~14.8-17.6 (slow) |
| Q8 | yes | 73k | 331-394.5 t/s | ~29.6-35.2 (slow) |
| Q4 | yes | 74k | 591.1-704.5 t/s | ~52.8-62.9 (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 ERNIE-Doc (247M)?▶
Yes. At Q4 it generates ~591.1-704.5 tok/s and fits up to 74k context; beyond that it spills to SSD swap and slows to ~52.8-62.9 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.