GPU comparison
Mac mini M6 (32GB) 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 64 tracked models each one can run.
| Mac mini M6 (32GB) | NVIDIA RTX 4090 (24GB) | |
|---|---|---|
| Memory | 32.0 GB | 24.0 GB |
| Bandwidth | 170 GB/s | 1008 GB/s |
| Price (approx) | $1,299 | $2,999 |
| LLMs it runs | 47 of 64 | 47 of 64 |
| Best model it runs | Qwen3.8 27B · 10–15 tok/s | Qwen3.8 27B · 38–57 tok/s |
Both run the same number of models, but the Mac mini M6 (32GB) has more memory (32.0 GB), so it can hold larger models at higher quality. The NVIDIA RTX 4090 (24GB) has more memory bandwidth (1008 GB/s), so it generates tokens faster at the same model and quant.