MacBook Air M4 (24 GB) vs M5 (24 GB) for local LLMs

The verdict is the new MacBook Air M5 (24 GB) at $1,499 (Apple list, 14 Nov 2026), unless a used M4 (24 GB) costs under about $1,250. The LLMCheck index puts Qwen 3.6-35B-A3B at ~59 tok/s (estimated) on the new Mac against ~50 tok/s (estimated) on the used one, and both fit the same 63 of the 130 models.

Bandwidth
120 / 153
GB/s
Unified memory
24 / 24
GB
Models that fit
63 / 63
of 130
Qwen 3.6-35B-A3B
estimated50 / estimated59
tok/s

Spec sheet: M4 (24 GB) vs M5 (24 GB)

M4 (24 GB)M5 (24 GB)
ChipM4M5
GPU cores10-core10-core
Memory bandwidth120 GB/s153 GB/s
Unified memory24 GB24 GB
Price—
used or refurbished only — check current listings
$1,499
Apple list price, checked 14 Nov 2026 · with 512GB storage
Price per GB—$62
Models that fit (of 130)6363
Best local LLM hereQwen 3.6-35B-A3B estimated50 tok/sQwen 3.6-35B-A3B estimated59 tok/s
Qwen 3.6-35B-A3Bestimated50 tok/sestimated59 tok/s
Price per tok/s on Qwen 3.6-35B-A3B—$25
Where to buyUsed / refurbished (Apple no longer sells it new)New · sold new by Apple (Amazon stock not verified)
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 MacBook Air M4 (24 GB) and MacBook Air M5 (24 GB) pages print, with its provenance mark. Across the 59 shared models with a figure on both, the M5 column is a median ×1.25 of the M4 column.

ModelSizeM4 tok/sM5 tok/sRatio
Qwen 3.6-35B-A3B35B MoEestimated50estimated59×1.18
Qwen3.8-27B27.8Bestimated7 slowestimated8 slow×1.14
Nanbeige4.3-33B33.1Bestimated5 slowestimated6 slow×1.20
Qwen 3.6-27B27Bestimated6 slowestimated8 slow×1.33
Recursive Flint39.8B MoEestimated56estimated67×1.20
KAT-Coder-V2.535B MoEestimated36estimated44×1.22
Muse Glimmer 30B30Bestimated4 slowestimated6 slow×1.50
LFM2.5-24B-A2B24B MoEcommunity59community74×1.25
Gemma 4 31B31Bestimated6 slowestimated7 slow×1.17
MiniCPM-V 4.7 35B-A3B35.2B MoEestimated44estimated52×1.18
Nemotron 3.5 Lightning30B MoEestimated34estimated41×1.21
Gemma 4 26B-A4B26B MoEestimated40estimated48×1.20
GLM-4.7-Flash31B MoEestimated37estimated45×1.22
Raon-1 mini preview28.8B MoEestimated45estimated54×1.20
North Mini Code 1.030.5B MoEestimated28community34×1.21
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 MacBook Air M4 (24 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 both have 24 GB. The difference is speed and price.

Price per GB and per token/s

The new M5 (24 GB) costs $1,499 (Apple list, 14 Nov 2026): $62 per GB and $25 per tok/s on Qwen 3.6-35B-A3B. A used M4 (24 GB) matches that $25 per tok/s at about $1,250; below that price it is the better value on decode speed alone. The index records no used prices: check current listings, and weigh the warranty, battery health and the remaining years of macOS support.

Which to buy, by use case

Bottom line: The new M5 (24 GB), unless the used one costs under about $1,250.

🛒 Where to buy these two Macs

Renewed stock of the 24 GB MacBook Air M4 varies: check the memory in the listing before you buy. The MacBook Air M5 (24 GB) is sold new by Apple; Amazon stock of the 24 GB configuration is not verified, so check the listing’s memory.

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: M4 (24 GB) vs M5 (24 GB)

Which is better for local LLMs, the MacBook Air M4 (24 GB) or the MacBook Air M5 (24 GB)?

The verdict is the new MacBook Air M5 (24 GB) at $1,499 (Apple list, 14 Nov 2026), unless a used M4 (24 GB) costs under about $1,250. The LLMCheck index puts Qwen 3.6-35B-A3B at ~59 tok/s (estimated) on the new Mac against ~50 tok/s (estimated) on the used one, and both fit the same 63 of the 130 models.

How much faster is the MacBook Air M5 (24 GB) than the MacBook Air M4 (24 GB) for local LLMs?

Decode speed on Apple Silicon follows memory bandwidth: the MacBook Air M5 (24 GB) reads memory at 153 GB/s, the MacBook Air M4 (24 GB) at 120 GB/s. The LLMCheck index puts Qwen 3.6-35B-A3B at ~59 tok/s (estimated) against ~50 tok/s (estimated). Across the 59 shared models with a figure on both, the median gain is 1.25x.

Do the MacBook Air M4 (24 GB) and the MacBook Air M5 (24 GB) run the same models?

Yes. Both fit the same 63 of the 130 models in the LLMCheck index.

What should a used MacBook Air M4 (24 GB) cost to beat a new MacBook Air M5 (24 GB)?

About $1,250 or less. At that price it matches the new Mac's $25 per tok/s on Qwen 3.6-35B-A3B ($1,499 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 MacBook Air M4 (24 GB): Qwen 3.6-35B-A3B at ~50 tok/s (estimated). On the MacBook Air M5 (24 GB): Qwen 3.6-35B-A3B at ~59 tok/s (estimated). 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