🔌
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 ADM?
Yes — here's how fast and up to what context, with real measured numbers.
ADM on the NVIDIA GeForce RTX 2050
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 59k | 73.1-87.2 t/s | ~6.5-7.8 (slow) |
| Q8 | yes | 68k | 146.3-174.3 t/s | ~13.1-15.6 (slow) |
| Q4 | yes | 72k | 261.2-311.3 t/s | ~23.3-27.8 (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 ADM?▶
Yes. At Q4 it generates ~261.2-311.3 tok/s and fits up to 72k context; beyond that it spills to SSD swap and slows to ~23.3-27.8 tok/s.
How much context fits?▶
At Q4, up to about 72k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.