🔌
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 Mobile run OPT-125M (finetuned on PTB)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-125M (finetuned on PTB) on the NVIDIA GeForce RTX 2050 Mobile
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 29k | 327-389.8 t/s | ~116.8-139.2 (slow) |
| Q8 | yes | 31k | 654.1-779.5 t/s | ~233.6-278.4 (slow) |
| Q4 | yes | 32k | 1168-1392 t/s | ~417.1-497.1 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
→ All models on the NVIDIA GeForce RTX 2050 Mobile
→ OPT-125M (finetuned on PTB) specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 2050 Mobile run OPT-125M (finetuned on PTB)?▶
Yes. At Q4 it generates ~1168-1392 tok/s and fits up to 32k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~417.1-497.1 tok/s.
How much context fits?▶
At Q4, up to about 32k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.