Mac Studio M3 Ultra (256 GB) vs M5 Max (128 GB) for local LLMs

For models above 128 GB the verdict is a used Mac Studio M3 Ultra (256 GB): it fits 15 more of the index's models, led by MiMo-V2.6-Flash at 59 tok/s (community run). For everything that fits in 128 GB the new M5 Max (128 GB) is a little slower and has a warranty.

Bandwidth
819 / 614
GB/s
Unified memory
256 / 128
GB
Models that fit
108 / 93
of 130
Qwen3.8-Flash-Next
estimated57 / community47
tok/s

Spec sheet: M3 Ultra (256 GB) vs M5 Max (128 GB)

M3 Ultra (256 GB)M5 Max (128 GB)
ChipM3 UltraM5 Max
GPU cores60- or 80-core40-core
Memory bandwidth819 GB/s614 GB/s
Unified memory256 GB128 GB
Price—
used or refurbished only — check current listings
$5,099
Apple list price, checked 14 Nov 2026 · with 512GB storage
Price per GB—$40
Models that fit (of 130)10893
Best local LLM hereMiMo-V2.6-Flash community59 tok/sQwen 3.6-35B-A3B community130 tok/s
Qwen3.8-Flash-Nextestimated57 tok/scommunity47 tok/s
Price per tok/s on Qwen3.8-Flash-Next—$108
Where to buyUsed / refurbished (Apple no longer sells it new)New · build-to-order from Apple
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 Studio M3 Ultra (256 GB) and Mac Studio M5 Max (128 GB) pages print, with its provenance mark. Across the 89 shared models with a figure on both, the M5 Max column is a median ×0.80 of the M3 Ultra column.

ModelSizeM3 Ultra tok/sM5 Max tok/sRatio
Qwen 3.6-35B-A3B35B MoEcommunity106community130×1.23
Qwen3.8-Flash-Next125B MoEestimated57community47×0.82
Recursive Flint39.8B MoEcommunity91community123×1.35
DeepSeek V4 Flash284B MoEestimated32community39×1.22
DeepSeek V4 Flash Vision-Exp305B MoEestimated32estimated39×1.22
GLM-5.3-Flash320B MoEestimated24estimated27×1.12
Inkling-Small caveat276B MoEestimated35estimated42×1.20
North Mini Code 1.030.5B MoEestimated133community120×0.90
Nemotron 3.5 Lightning30B MoEestimated151community117×0.77
LFM2.5-24B-A2B24B MoEcommunity116sourced184×1.59
Qwen3.8-27B27.8Bcommunity38community31×0.82
KAT-Coder-V2.535B MoEestimated100community89×0.89
Qwen3-235B-A22B235B MoEestimated32estimated26×0.81
Nanbeige4.3-33B33.1Bestimated35community25×0.71
Raon-1 mini preview28.8B MoEestimated136estimated123×0.90
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Showing the top 15 of the 93 shared models, in Best-by-Mac suitability order for the Mac Studio M5 Max (128 GB). Every other pair of Macs: the compare tool’s two-Mac mode.

What only one of them runs

A model fits when its minimum RAM (its smallest build of at least 3 bits with a working Mac runtime, plus about 2 GB for the runtime and a short context; 2-bit only where a published Mac run used it) is at most the Mac’s unified memory. The extra memory unlocks these models from the LLMCheck index:

Only the M3 Ultra (256 GB): 15 more

ModelSizeMin RAMM3 Ultra tok/s
MiMo-V2.6-Flash309B MoE170 GBcommunity59
Inkling 2 Small caveat594B MoE228 GBestimated36
GLM 5.2753B MoE256 GBestimated15
MiniMax-M3428B MoE162 GBestimated29
GLM-5.3753B MoE256 GBestimated11
MiniMax-M3.1-Flash428B MoE189 GBcommunity26
Beam 1.0 caveat501.3B MoE199 GBestimated19
MiniMax M2.5230B MoE130 GBestimated41
Hunyuan Hy3295B MoE160 GBestimated21
Nemotron 3 Ultra 550B-A55B550B MoE226 GBestimated12

Top 10 of 15 by suitability; the full list is on the Mac Studio M3 Ultra (256 GB) page.

Price per GB and per token/s

The new M5 Max (128 GB) costs $5,099 (Apple list, 14 Nov 2026): $40 per GB and $108 per tok/s on Qwen3.8-Flash-Next. A used M3 Ultra (256 GB) matches that $108 per tok/s at about $6,200; it decodes faster, so any used price below that buys more speed per dollar than the new Mac. Its real case is the 15 models that need more than 128 GB, which the new Mac cannot load at any price. The index records no used prices: check current listings, and weigh the warranty and the remaining years of macOS support.

Which to buy, by use case

Bottom line: A used M3 Ultra (256 GB) for the 15 models above 128 GB; the new M5 Max (128 GB) for the rest.

🛒 Where to buy these two Macs

Renewed stock of the 256 GB Mac Studio M3 Ultra varies: check the memory in the listing before you buy. Amazon does not stock the Mac Studio M5 Max (128 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; Apple’s M5-generation GPUs add per-core Neural Accelerators aimed at that work.

FAQ: M3 Ultra (256 GB) vs M5 Max (128 GB)

Which is better for local LLMs, the Mac Studio M3 Ultra (256 GB) or the Mac Studio M5 Max (128 GB)?

For models above 128 GB the verdict is a used Mac Studio M3 Ultra (256 GB): it fits 15 more of the index's models, led by MiMo-V2.6-Flash at 59 tok/s (community run). For everything that fits in 128 GB the new M5 Max (128 GB) is a little slower and has a warranty.

How much faster is the Mac Studio M3 Ultra (256 GB) than the Mac Studio M5 Max (128 GB) for local LLMs?

Decode speed on Apple Silicon follows memory bandwidth: the Mac Studio M3 Ultra (256 GB) reads memory at 819 GB/s, the Mac Studio M5 Max (128 GB) at 614 GB/s. The LLMCheck index puts Qwen3.8-Flash-Next at ~57 tok/s (estimated) against 47 tok/s (community run). Across the 89 shared models with a figure on both, the median gain is 1.25x.

What can the Mac Studio M3 Ultra (256 GB) run that the Mac Studio M5 Max (128 GB) cannot?

15 models in the LLMCheck index need more than 128 GB but fit in 256 GB, led by MiMo-V2.6-Flash, Inkling 2 Small, GLM 5.2. Both run the other 93.

What should a used Mac Studio M3 Ultra (256 GB) cost to beat a new Mac Studio M5 Max (128 GB)?

About $6,200 or less. At that price it matches the new Mac's $108 per tok/s on Qwen3.8-Flash-Next ($5,099 at Apple list, checked 14 Nov 2026). The LLMCheck index records no used prices, so check current listings, and weigh warranty and macOS support.

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

On the Mac Studio M3 Ultra (256 GB): MiMo-V2.6-Flash at 59 tok/s (community run). On the Mac Studio M5 Max (128 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.

Related