GPU comparison
Mac Studio M2 Ultra (64GB) vs NVIDIA RTX 4080 (16GB) 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.
| Mac Studio M2 Ultra (64GB) | NVIDIA RTX 4080 (16GB) | |
|---|---|---|
| Memory | 64.0 GB | 16.0 GB |
| Bandwidth | 800 GB/s | 717 GB/s |
| Price (approx) | $3,999 | $999 |
| LLMs it runs | 16 of 18 | 12 of 18 |
| Best model it runs | Gemma 4 31B · 15–23 tok/s | Gemma 4 26B-A4B (MoE) · 107–161 tok/s |
The Mac Studio M2 Ultra (64GB) runs 4 more of the tracked models (16 vs 12), thanks to its 64.0 GB of memory. The Mac Studio M2 Ultra (64GB) has more memory bandwidth (800 GB/s), so it generates tokens faster at the same model and quant.