GPU comparison
MacBook Pro M5 Pro (24GB) vs NVIDIA RTX 6000 Ada (48GB) 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 6000 Ada (48GB) | |
|---|---|---|
| Memory | 24.0 GB | 48.0 GB |
| Bandwidth | 307 GB/s | 960 GB/s |
| Price (approx) | $2,199 | $6,800 |
| LLMs it runs | 45 of 64 | 52 of 64 |
| Best model it runs | Qwen3.8 27B · 14–21 tok/s | Qwen3.8 27B · 23–34 tok/s |
The NVIDIA RTX 6000 Ada (48GB) runs 7 more of the tracked models (52 vs 45), thanks to its 48.0 GB of memory. The NVIDIA RTX 6000 Ada (48GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.