🔌
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 Base (151M, WT103)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc Base (151M, WT103) on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 72k | 270.7-322.6 t/s | ~24.2-28.8 (slow) |
| Q8 | yes | 74k | 541.5-645.3 t/s | ~48.3-57.6 (slow) |
| Q4 | yes | 75k | 966.9-1152.3 t/s | ~86.3-102.9 (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 Base (151M, WT103)?▶
Yes. At Q4 it generates ~966.9-1152.3 tok/s and fits up to 75k context; beyond that it spills to SSD swap and slows to ~86.3-102.9 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.