GPU comparison
NVIDIA RTX 5090 (32GB) 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 18 tracked models each one can run.
| NVIDIA RTX 5090 (32GB) | AMD RX 7900 XTX (24GB) | |
|---|---|---|
| Memory | 32.0 GB | 24.0 GB |
| Bandwidth | 1792 GB/s | 960 GB/s |
| Price (approx) | $2,499 | $899 |
| LLMs it runs | 15 of 18 | 15 of 18 |
| Best model it runs | Gemma 4 31B · 55–83 tok/s | Gemma 4 31B · 32–48 tok/s |
Both run the same number of models, but the NVIDIA RTX 5090 (32GB) has more memory (32.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 5090 (32GB) has more memory bandwidth (1792 GB/s), so it generates tokens faster at the same model and quant.