Mac mini (M5 Pro) for local AI.
With 64 GB it runs Qwen3.8 27B (needs 22.7 GB). 77 models fit. Published speed: gpt-oss-20b at 76.6 tokens/sec.
Memory24 / 48 / 64 GB
Shared between CPU and graphics.
Bandwidth307 GB/s
Higher means faster answers.
PriceFrom about $1,699
As of 2026-10-15. Check before buying.
By memory option.
| Memory | Usable | Models that fit | Best three |
|---|---|---|---|
| 24 GB | 18 GB | 45 | K2 Horizon 7B (8.6 GB), Gemma 4 12B (11.2 GB), Qwen3.5 9B (9.6 GB) |
| 48 GB | 36 GB | 76 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
| 64 GB | 48 GB | 77 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
Published speeds.
Measured by others, with sources. Not our tests.
| Model | Tokens/sec | Engine | Setup | Source |
|---|---|---|---|---|
| gpt-oss-20b | 76.6 | oMLX v0.6.2 · MXFP4-Q8 (MLX) | M5 Pro 20-core GPU, 48GB (chip-level result; device not stated) | community-measured · 2026-10-15 |
Short answers.
- What is the best local LLM for the Mac mini (M5 Pro)?
- With 64 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 77 of 124 models fit. With 24 GB: K2 Horizon 7B.
- How fast is the Mac mini (M5 Pro) for local AI?
- Published: gpt-oss-20b at 76.6 tokens/sec (oMLX v0.6.2, M5 Pro 20-core GPU, 48GB (chip-level result; device not stated)). These are other people's measurements, not ours.
- How much does the Mac mini (M5 Pro) cost?
- From about $1,699 (as of 2026-10-15). 2026 prices are inflated by the memory-chip shortage; check before buying.
Specs from Apple – Mac mini tech specs (2026-10-15). Prices are approximate and dated; 2026 prices are inflated by the memory-chip shortage.
# Mac mini (M5 Pro) for local AI URL: https://insidethemachine.ai/machines/mac-mini-m5-pro Type: Mac desktop. Chip: M5 Pro (16- or 20-core GPU). Memory: unified, options 24, 48, 64 GB. Bandwidth: 307 GB/s. Spec source: https://www.apple.com/mac-mini/specs/ (2026-10-15). Price: from about $1,699 (2026-10-15, approximate). Status: current. ## Which models fit | memory GB | usable GB | models that fit | best 3 | |---|---|---|---| | 24 | 18 | 45 | K2 Horizon 7B (8.6 GB), Gemma 4 12B (11.2 GB), Qwen3.5 9B (9.6 GB) | | 48 | 36 | 76 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) | | 64 | 48 | 77 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) | ## Published speeds (not our tests) - gpt-oss-20b: 76.6 tok/s decode, 1611 tok/s prompt (oMLX v0.6.2, MXFP4-Q8 (MLX), M5 Pro 20-core GPU, 48GB (chip-level result; device not stated), community-measured) https://omlx.ai/benchmarks/performance/h03e0nvx (2026-10-15) ## Questions **What is the best local LLM for the Mac mini (M5 Pro)?** With 64 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 77 of 124 models fit. With 24 GB: K2 Horizon 7B. **How fast is the Mac mini (M5 Pro) for local AI?** Published: gpt-oss-20b at 76.6 tokens/sec (oMLX v0.6.2, M5 Pro 20-core GPU, 48GB (chip-level result; device not stated)). These are other people's measurements, not ours. **How much does the Mac mini (M5 Pro) cost?** From about $1,699 (as of 2026-10-15). 2026 prices are inflated by the memory-chip shortage; check before buying.