Mac mini M6 (32 GB) vs M5 Pro (24 GB) for local LLMs

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.

Bandwidth
170 / 307
GB/s
Unified memory
32 / 24
GB
Models that fit
63 / 63
of 130
Qwen3.8-27B
community10 / sourced17
tok/s

Spec sheet: M6 (32 GB) vs M5 Pro (24 GB)

M6 (32 GB)M5 Pro (24 GB)
ChipM6M5 Pro
GPU cores12-core16- or 20-core
Memory bandwidth170 GB/s307 GB/s
Unified memory32 GB24 GB
Price$1,299
Apple list price, checked 14 Nov 2026 · with 256GB storage
$1,699
Apple list price, checked 14 Nov 2026 · with 512GB storage
Price per GB$41$71
Models that fit (of 130)6363
Best local LLM hereQwen 3.6-35B-A3B community59 tok/sLFM2.5-24B-A2B community114 tok/s
Qwen3.8-27Bcommunity10 tok/ssourced17 tok/s
Price per tok/s on Qwen3.8-27B$130$100
Where to buyNew · build-to-order from AppleNew · Amazon stocks this configuration
Bandwidth and RAM per configuration from data/macs.json (Apple’s figures); prices are Apple’s US list prices on the date shown. “Best local LLM” is the Best by Mac headline pick for each config. Winners in bold.

The models both run, side by side

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.

ModelSizeM6 tok/sM5 Pro tok/sRatio
Qwen 3.6-35B-A3B35B MoEcommunity59estimated79×1.34
Qwen3.8-27B27.8Bcommunity10 slowsourced17×1.70
Nanbeige4.3-33B33.1Bestimated7 slowestimated12 slow×1.71
Qwen 3.6-27B27Bestimated9 slowestimated15×1.67
KAT-Coder-V2.535B MoEestimated47estimated72×1.53
LFM2.5-24B-A2B24B MoEestimated79community114×1.44
Recursive Flint39.8B MoEestimated61estimated92×1.51
Muse Glimmer 30B30Bcommunity9 slowestimated11 slow×1.22
MiniCPM-V 4.7 35B-A3B35.2B MoEestimated54estimated54×1.00
Nemotron 3.5 Lightning30B MoEcommunity45community72×1.60
Gemma 4 31B31Bcommunity8 slowestimated13 slow×1.62
Raon-1 mini preview28.8B MoEestimated58community86×1.48
Gemma 4 26B-A4B26B MoEcommunity49estimated78×1.59
GLM-4.7-Flash31B MoEcommunity47estimated73×1.55
North Mini Code 1.030.5B MoEestimated37community70×1.89
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Showing the top 15 of the 63 shared models, in Best-by-Mac suitability order for the Mac mini M6 (32 GB). Every other pair of Macs: the compare tool’s two-Mac mode.

What only one of them runs

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.

Price per GB and per token/s

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.

Which to buy, by use case

Bottom line: The M5 Pro (24 GB): a median 1.7× the speed for $400 more.

🛒 Where to buy these two Macs

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.

Where these numbers come from

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.

FAQ: M6 (32 GB) vs M5 Pro (24 GB)

Which is better for local LLMs, the Mac mini M6 (32 GB) or the Mac mini M5 Pro (24 GB)?

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.

How much faster is the Mac mini M5 Pro (24 GB) than the Mac mini M6 (32 GB) for local LLMs?

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.

Do the Mac mini M6 (32 GB) and the Mac mini M5 Pro (24 GB) run the same models?

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.

Is the Mac mini M5 Pro (24 GB) worth $400 more than the Mac mini M6 (32 GB)?

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.

What is the best local LLM for each of these Macs?

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.

Related