Local AI Hardware / GPUs for local AI
AMD Radeon RX 7900 XTX 24GB for local AI
Sold prices for the AMD Radeon RX 7900 XTX 24GB are tracked every day on GPU Sold (https://gpusold.com/gpu/rx-7900-xtx).
24 GB with ROCm support; good bandwidth for the price.
- Memory
- 24 GB
- Memory bandwidth
- 960 GB/s
- Board power
- 355 W
- Architecture
- RDNA 3
Before you buy a used GPU for AI
- Memory first. The model and its context have to fit in VRAM (or it spills to system RAM and slows to a crawl). Use the VRAM calculator.
- Bandwidth second. Token generation speed is mostly limited by memory bandwidth, not compute.
- Check memory temperatures under load on GDDR6X cards (3090, 3090 Ti). Worn thermal pads are common on ex-mining cards.
- Plan power and slot spacing before buying two or more cards. Transient spikes on high-end cards trip undersized power supplies.