GPU comparison
Mac mini M6 (16GB) vs NVIDIA RTX 5070 (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 (16GB) | NVIDIA RTX 5070 (12GB) | |
|---|---|---|
| Memory | 16.0 GB | 12.0 GB |
| Bandwidth | 153 GB/s | 672 GB/s |
| Price (approx) | $899 | $629 |
| LLMs it runs | 27 of 64 | 27 of 64 |
| Best model it runs | Devstral Small 2 24B · 10–15 tok/s | Devstral Small 2 24B · 45–68 tok/s |
Both run the same number of models, but the Mac mini M6 (16GB) has more memory (16.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 5070 (12GB) has more memory bandwidth (672 GB/s), so it generates tokens faster at the same model and quant.