GPU comparison
Mac Studio M2 Ultra (192GB) 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 18 tracked models each one can run.
| Mac Studio M2 Ultra (192GB) | NVIDIA RTX 4090 (24GB) | |
|---|---|---|
| Memory | 192.0 GB | 24.0 GB |
| Bandwidth | 800 GB/s | 1008 GB/s |
| Price (approx) | $5,599 | $1,599 |
| LLMs it runs | 16 of 18 | 15 of 18 |
| Best model it runs | Gemma 4 31B · 13–19 tok/s | Gemma 4 31B · 33–50 tok/s |
The Mac Studio M2 Ultra (192GB) runs 1 more of the tracked models (16 vs 15), thanks to its 192.0 GB of memory. The NVIDIA RTX 4090 (24GB) has more memory bandwidth (1008 GB/s), so it generates tokens faster at the same model and quant.