GPU comparison
MacBook Pro M5 Pro (24GB) vs NVIDIA RTX 5080 (16GB) 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.
| MacBook Pro M5 Pro (24GB) | NVIDIA RTX 5080 (16GB) | |
|---|---|---|
| Memory | 24.0 GB | 16.0 GB |
| Bandwidth | 307 GB/s | 960 GB/s |
| Price (approx) | $2,199 | $1,399 |
| LLMs it runs | 45 of 64 | 45 of 64 |
| Best model it runs | Qwen3.8 27B · 14–21 tok/s | Qwen3.8 27B · 54–82 tok/s |
Both run the same number of models, but the MacBook Pro M5 Pro (24GB) has more memory (24.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 5080 (16GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.