The verdict is the Mac mini M5 Pro (24 GB), if the $400 premium fits: the LLMCheck index’s figures put it a median 1.7× faster across the 61 shared models with a figure on both; on Qwen3.8-27B, 17 tok/s (published figure) against 10 (community run). That is 307 GB/s of memory bandwidth against 170 GB/s.
| M6 (32 GB) | M5 Pro (24 GB) | |
|---|---|---|
| Chip | M6 | M5 Pro |
| GPU cores | 12-core | 16- or 20-core |
| Memory bandwidth | 170 GB/s | 307 GB/s |
| Unified memory | 32 GB | 24 GB |
| Price | $1,299 | $1,699 |
| Price per GB | $41 | $71 |
| Models that fit (of 130) | 63 | 63 |
| Best local LLM here | Qwen 3.6-35B-A3B community59 tok/s | LFM2.5-24B-A2B community114 tok/s |
| Qwen3.8-27B | community10 tok/s | sourced17 tok/s |
| Price per tok/s on Qwen3.8-27B | $130 | $100 |
| Where to buy | New · build-to-order from Apple | New · Amazon stocks this configuration |
Every speed below is the LLMCheck index’s figure for that exact configuration — the same number its Mac mini M6 (32 GB) and Mac mini M5 Pro (24 GB) pages print, with its provenance mark. Across the 61 shared models with a figure on both, the M5 Pro column is a median ×1.71 of the M6 column.
| Model | Size | M6 tok/s | M5 Pro tok/s | Ratio |
|---|---|---|---|---|
| Qwen 3.6-35B-A3B | 35B MoE | community59 | estimated79 | ×1.34 |
| Qwen3.8-27B | 27.8B | community10 slow | sourced17 | ×1.70 |
| Nanbeige4.3-33B | 33.1B | estimated7 slow | estimated12 slow | ×1.71 |
| Qwen 3.6-27B | 27B | estimated9 slow | estimated15 | ×1.67 |
| KAT-Coder-V2.5 | 35B MoE | estimated47 | estimated72 | ×1.53 |
| LFM2.5-24B-A2B | 24B MoE | estimated79 | community114 | ×1.44 |
| Recursive Flint | 39.8B MoE | estimated61 | estimated92 | ×1.51 |
| Muse Glimmer 30B | 30B | community9 slow | estimated11 slow | ×1.22 |
| MiniCPM-V 4.7 35B-A3B | 35.2B MoE | estimated54 | estimated54 | ×1.00 |
| Nemotron 3.5 Lightning | 30B MoE | community45 | community72 | ×1.60 |
| Gemma 4 31B | 31B | community8 slow | estimated13 slow | ×1.62 |
| Raon-1 mini preview | 28.8B MoE | estimated58 | community86 | ×1.48 |
| Gemma 4 26B-A4B | 26B MoE | community49 | estimated78 | ×1.59 |
| GLM-4.7-Flash | 31B MoE | community47 | estimated73 | ×1.55 |
| North Mini Code 1.0 | 30.5B MoE | estimated37 | community70 | ×1.89 |
Nothing: both fit the same 63 of the 130 models in the LLMCheck index, because no catalog model’s minimum RAM falls between 24 and 32 GB. The difference is speed and price, plus context headroom: the extra memory holds a longer KV cache beside the same weights.
At Apple’s list prices the M6 (32 GB) costs $41 per GB of unified memory and the M5 Pro (24 GB) $71. On Qwen3.8-27B — the reference model here, which both run — that is $130 and $100 per tok/s of decode speed: the M5 Pro (24 GB) buys more speed per dollar.
The $400 premium (31% more) buys +70% decode speed on Qwen3.8-27B.
Bottom line: The M5 Pro (24 GB): a median 1.7× the speed for $400 more.
Amazon does not stock the Mac mini M6 (32 GB): Apple builds it to order.
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.
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 mini M5 Pro (24 GB), if the $400 premium fits: the LLMCheck index’s figures put it a median 1.7× faster across the 61 shared models with a figure on both; on Qwen3.8-27B, 17 tok/s (published figure) against 10 (community run). That is 307 GB/s of memory bandwidth against 170 GB/s.
Decode speed on Apple Silicon follows memory bandwidth: the Mac mini M5 Pro (24 GB) reads memory at 307 GB/s, the Mac mini M6 (32 GB) at 170 GB/s. The LLMCheck index puts Qwen3.8-27B at 17 tok/s (published figure) against 10 tok/s (community run). Across the 61 shared models with a figure on both, the median gain is 1.71x.
Yes. Both fit the same 63 of the 130 models in the LLMCheck index; the extra 8 GB on the Mac mini M6 (32 GB) is headroom for longer contexts and other apps, not extra models.
It costs $1,699 against $1,299 (Apple list prices, checked 14 Nov 2026; the M5 Pro (24 GB) price includes 512GB of storage, the M6 (32 GB) price 256GB). For that it gives 17 tok/s (published figure) against 10 tok/s (community run) on Qwen3.8-27B. 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 M6 (32 GB): Qwen 3.6-35B-A3B at 59 tok/s (community run). On the Mac mini M5 Pro (24 GB): LFM2.5-24B-A2B at 114 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.