GPU comparison
MacBook Pro M5 Pro (24GB) vs NVIDIA RTX 4090 (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.
| MacBook Pro M5 Pro (24GB) | NVIDIA RTX 4090 (24GB) | |
|---|---|---|
| Memory | 24.0 GB | 24.0 GB |
| Bandwidth | 307 GB/s | 1008 GB/s |
| Price (approx) | $2,199 | $2,999 |
| LLMs it runs | 45 of 64 | 47 of 64 |
| Best model it runs | Qwen3.8 27B · 14–21 tok/s | Qwen3.8 27B · 38–57 tok/s |
The NVIDIA RTX 4090 (24GB) runs 2 more of the tracked models (47 vs 45). With the same nominal memory, more of it is usable for model weights on this architecture. The NVIDIA RTX 4090 (24GB) has more memory bandwidth (1008 GB/s), so it generates tokens faster at the same model and quant.