GPU comparison
NVIDIA RTX 5080 (16GB) vs AMD RX 7900 XTX (24GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 64 tracked models each one can run.
| NVIDIA RTX 5080 (16GB) | AMD RX 7900 XTX (24GB) | |
|---|---|---|
| Memory | 16.0 GB | 24.0 GB |
| Bandwidth | 960 GB/s | 960 GB/s |
| Price (approx) | $1,399 | $949 |
| LLMs it runs | 45 of 64 | 47 of 64 |
| Best model it runs | Qwen3.8 27B · 54–82 tok/s | Qwen3.8 27B · 36–54 tok/s |
The AMD RX 7900 XTX (24GB) runs 2 more of the tracked models (47 vs 45), thanks to its 24.0 GB of memory.