GPU comparison
Mac mini M6 (24GB) vs AMD RX 9070 XT (16GB) 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) | AMD RX 9070 XT (16GB) | |
|---|---|---|
| Memory | 24.0 GB | 16.0 GB |
| Bandwidth | 170 GB/s | 645 GB/s |
| Price (approx) | $1,099 | $699 |
| LLMs it runs | 45 of 64 | 45 of 64 |
| Best model it runs | Qwen3.8 27B · 10–15 tok/s | Qwen3.8 27B · 38–58 tok/s |
Both run the same number of models, but the Mac mini M6 (24GB) has more memory (24.0 GB), so it can hold larger models at higher quality. The AMD RX 9070 XT (16GB) has more memory bandwidth (645 GB/s), so it generates tokens faster at the same model and quant.