🔌
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 MiniCPM-2.4B?
Yes — here's how fast and up to what context, with real measured numbers.
MiniCPM-2.4B on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2k | 16.7-20 t/s | ~1.5-1.8 (slow) |
| Q8 | yes | 39k | 33.5-39.9 t/s | ~3-3.6 (slow) |
| Q4 | yes | 55k | 59.8-71.3 t/s | ~5.3-6.4 (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 MiniCPM-2.4B?▶
Yes. At Q4 it generates ~59.8-71.3 tok/s and fits up to 55k context; beyond that it spills to SSD swap and slows to ~5.3-6.4 tok/s.
How much context fits?▶
At Q4, up to about 55k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.