GPU comparison
Mac mini M6 (32GB) vs NVIDIA RTX 3060 (12GB) 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.
| Mac mini M6 (32GB) | NVIDIA RTX 3060 (12GB) | |
|---|---|---|
| Memory | 32.0 GB | 12.0 GB |
| Bandwidth | 170 GB/s | 360 GB/s |
| Price (approx) | $1,299 | $329 |
| LLMs it runs | 47 of 64 | 27 of 64 |
| Best model it runs | Qwen3.8 27B · 10–15 tok/s | Devstral Small 2 24B · 26–39 tok/s |
The Mac mini M6 (32GB) runs 20 more of the tracked models (47 vs 27), thanks to its 32.0 GB of memory. The NVIDIA RTX 3060 (12GB) has more memory bandwidth (360 GB/s), so it generates tokens faster at the same model and quant.