Best Macs and mini PCs for local AI
Ranked by what each one runs fully in memory at 32k context, with prices in Canada today.
In short
The top pick in Canada right now is the ASUS Ascent GX10 128GB, $8,299 at Amazon: it runs gpt-oss 120B fully in memory at 32k context at about 23 tok/s (estimated). Ranked by the most capable open model each one runs fully in memory at 32k context and a usable speed, then by how many models it runs, then by speed on Qwen 3.8 27B, then by price.
Updated . Speeds are estimates; how they are worked out.
The list
Best first. Speeds are estimates est.
| # | Machine | Memory | Price | Best model it runs at 32k | Models in memory | Qwen 3.8 27B | tok/s per $1,000 |
|---|---|---|---|---|---|---|---|
| 1 | ASUS Ascent GX10 128GB | 128 GB | $8,299Amazon | gpt-oss 120BMXFP423 tok/s | 22 | 5 tok/s | 0.7 |
| 2 | GMKtec EVO-X2 Ryzen AI Max+ 395 128GB | 128 GB | $5,099Amazon | gpt-oss 120BMXFP420 tok/s | 18 | 5 tok/s | 0.9 |
| 3 | Mac mini M4 16GB | 16 GB | $1,399Amazon | LFM2.5 8B-A1BQ8_018 tok/s | 5 | won't run | – |
Questions
- What is the best Mac or mini PC for running AI models locally?
- The top pick in Canada right now is the ASUS Ascent GX10 128GB, $8,299 at Amazon: it runs gpt-oss 120B fully in memory at 32k context at about 23 tok/s (estimated).
- Which gives the most speed for the money?
- The GMKtec EVO-X2 Ryzen AI Max+ 395 128GB: about 5 tok/s on Qwen 3.8 27B for $5,099, the most tokens per second per unit of price on this list (estimated).
- What is the cheapest option here that runs Qwen 3.8 27B fully in memory?
- The GMKtec EVO-X2 Ryzen AI Max+ 395 128GB, $5,099 at Amazon, at about 5 tok/s at 32k context (estimated).