GPU comparison
Mac mini M6 (24GB) vs NVIDIA RTX 5060 (8GB) 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 (24GB) | NVIDIA RTX 5060 (8GB) | |
|---|---|---|
| Memory | 24.0 GB | 8.0 GB |
| Bandwidth | 170 GB/s | 448 GB/s |
| Price (approx) | $1,099 | $449 |
| LLMs it runs | 45 of 64 | 22 of 64 |
| Best model it runs | Qwen3.8 27B · 10–15 tok/s | Gemma 4 12B · 55–83 tok/s |
The Mac mini M6 (24GB) runs 23 more of the tracked models (45 vs 22), thanks to its 24.0 GB of memory. The NVIDIA RTX 5060 (8GB) has more memory bandwidth (448 GB/s), so it generates tokens faster at the same model and quant.