The verdict is the Mac Studio M5 Max (64 GB), if the $800 premium fits: the LLMCheck index’s figures put it a median 1.8× faster across the 75 shared models with a figure on both; on Qwen 3.6-35B-A3B, 130 against 79 tok/s (both community runs). That is 614 GB/s of memory bandwidth against 307 GB/s.
| Mac mini M5 Pro (64 GB) | Mac Studio M5 Max (64 GB) | |
|---|---|---|
| Chip | M5 Pro | M5 Max |
| GPU cores | 16- or 20-core | 40-core |
| Memory bandwidth | 307 GB/s | 614 GB/s |
| Unified memory | 64 GB | 64 GB |
| Price | $2,699 | $3,499 |
| Price per GB | $42 | $55 |
| Models that fit (of 130) | 77 | 77 |
| Best local LLM here | LFM2.5-24B-A2B community114 tok/s | Qwen 3.6-35B-A3B community130 tok/s |
| Qwen 3.6-35B-A3B | community79 tok/s | community130 tok/s |
| Price per tok/s on Qwen 3.6-35B-A3B | $34 | $27 |
| Form factor | a small desktop (bring your own display) | a desktop (bring your own display) |
| Where to buy | New · build-to-order from Apple | New · build-to-order from Apple |
Every speed below is the LLMCheck index’s figure for that exact configuration — the same number its Mac mini M5 Pro (64 GB) and Mac Studio M5 Max (64 GB) pages print, with its provenance mark. Across the 75 shared models with a figure on both, the Mac Studio M5 Max column is a median ×1.82 of the Mac mini M5 Pro column.
| Model | Size | Mac mini M5 Pro tok/s | Mac Studio M5 Max tok/s | Ratio |
|---|---|---|---|---|
| LFM2.5-24B-A2B | 24B MoE | community114 | sourced184 | ×1.61 |
| Qwen3.8-27B | 27.8B | sourced17 | community31 | ×1.82 |
| Recursive Flint | 39.8B MoE | community92 | community123 | ×1.34 |
| KAT-Coder-V2.5 | 35B MoE | estimated72 | community89 | ×1.24 |
| Qwen 3.6-35B-A3B | 35B MoE | community79 | community130 | ×1.65 |
| Nanbeige4.3-33B | 33.1B | estimated12 slow | community25 | ×2.08 |
| Ling-3.0-flash-VL | 124B MoE | estimated37 | estimated53 | ×1.43 |
| Qwen 3.6-27B | 27B | estimated15 | estimated30 | ×2.00 |
| Nemotron 3.5 Lightning | 30B MoE | community72 | community117 | ×1.62 |
| North Mini Code 1.0 | 30.5B MoE | community70 | community120 | ×1.71 |
| Gemma 4 26B-A4B | 26B MoE | estimated78 | sourced107 | ×1.37 |
| Raon-1 mini preview | 28.8B MoE | community86 | estimated123 | ×1.43 |
| GLM-4.7-Flash | 31B MoE | estimated73 | estimated107 | ×1.47 |
| Nemotron 3.5 Bolt 74B-A9B caveat | 74B MoE | estimated31 | community58 | ×1.87 |
| Muse Glimmer 30B | 30B | estimated11 slow | sourced27 | ×2.45 |
Nothing: both fit the same 77 of the 130 models in the LLMCheck index, because both have 64 GB. The difference is speed and price.
At Apple’s list prices the Mac mini M5 Pro (64 GB) costs $42 per GB of unified memory and the Mac Studio M5 Max (64 GB) $55. On Qwen 3.6-35B-A3B — the reference model here, which both run — that is $34 and $27 per tok/s of decode speed: the Mac Studio M5 Max (64 GB) buys more speed per dollar.
The $800 premium (30% more) buys +65% decode speed on Qwen 3.6-35B-A3B.
Bottom line: The Mac Studio M5 Max (64 GB): a median 1.8× the speed for $800 more.
Amazon does not stock either configuration: Apple builds both to order.
Each speed is decode (generation) tok/s from the LLMCheck index for that exact configuration: the lower-median measured run on that chip where one exists (a filled square is a published figure, a hollow circle a community run), otherwise an estimate from the memory-bandwidth model (hollow diamond, printed with a tilde). LLMCheck runs no tests of its own. Prompt processing (prefill) depends on GPU compute rather than bandwidth, and the index does not estimate it.
The verdict is the Mac Studio M5 Max (64 GB), if the $800 premium fits: the LLMCheck index’s figures put it a median 1.8× faster across the 75 shared models with a figure on both; on Qwen 3.6-35B-A3B, 130 against 79 tok/s (both community runs). That is 614 GB/s of memory bandwidth against 307 GB/s.
Decode speed on Apple Silicon follows memory bandwidth: the Mac Studio M5 Max (64 GB) reads memory at 614 GB/s, the Mac mini M5 Pro (64 GB) at 307 GB/s. The LLMCheck index puts Qwen 3.6-35B-A3B at 130 tok/s (community run) against 79 tok/s (community run). Across the 75 shared models with a figure on both, the median gain is 1.82x.
Yes. Both fit the same 77 of the 130 models in the LLMCheck index.
It costs $3,499 against $2,699 (Apple list prices, checked 14 Nov 2026). For that it gives 130 tok/s (community run) against 79 tok/s (community run) on Qwen 3.6-35B-A3B. Worth it if you use the extra speed or models daily; the cheaper Mac still runs every model the dearer one does.
On the Mac mini M5 Pro (64 GB): LFM2.5-24B-A2B at 114 tok/s (community run). On the Mac Studio M5 Max (64 GB): Qwen 3.6-35B-A3B at 130 tok/s (community run). These are the headline picks of the LLMCheck Best by Mac pages: the best-ranked model that reaches 15 tok/s on that Mac and has a standard Mac runtime.