The verdict is the MacBook Pro M5 Pro (24 GB), if the $1,000 premium fits: the LLMCheck index’s figures put it a median 1.9× faster across the 60 shared models with a figure on both; on LFM2.5-24B-A2B, 114 against 74 tok/s (both community runs). That is 307 GB/s of memory bandwidth against 153 GB/s.
| MacBook Air M5 (24 GB) | MacBook Pro M5 Pro (24 GB) | |
|---|---|---|
| Chip | M5 | M5 Pro |
| GPU cores | 10-core | 16- or 20-core |
| Memory bandwidth | 153 GB/s | 307 GB/s |
| Unified memory | 24 GB | 24 GB |
| Price | $1,499 | $2,499 |
| Price per GB | $62 | $104 |
| Models that fit (of 130) | 63 | 63 |
| Best local LLM here | Qwen 3.6-35B-A3B estimated59 tok/s | LFM2.5-24B-A2B community114 tok/s |
| LFM2.5-24B-A2B | community74 tok/s | community114 tok/s |
| Price per tok/s on LFM2.5-24B-A2B | $20 | $22 |
| Form factor | a fanless laptop with a battery and a built-in display | a laptop with a battery and a built-in display |
| Where to buy | New · sold new by Apple (Amazon stock not verified) | New · Amazon stocks this configuration |
Every speed below is the LLMCheck index’s figure for that exact configuration — the same number its MacBook Air M5 (24 GB) and MacBook Pro M5 Pro (24 GB) pages print, with its provenance mark. Across the 60 shared models with a figure on both, the MB Pro M5 Pro column is a median ×1.88 of the MB Air M5 column.
| Model | Size | MB Air M5 tok/s | MB Pro M5 Pro tok/s | Ratio |
|---|---|---|---|---|
| Qwen 3.6-35B-A3B | 35B MoE | estimated59 | estimated79 | ×1.34 |
| Qwen3.8-27B | 27.8B | estimated8 slow | sourced17 | ×2.12 |
| Nanbeige4.3-33B | 33.1B | estimated6 slow | estimated12 slow | ×2.00 |
| Recursive Flint | 39.8B MoE | estimated67 | estimated92 | ×1.37 |
| Qwen 3.6-27B | 27B | estimated8 slow | estimated15 | ×1.88 |
| KAT-Coder-V2.5 | 35B MoE | estimated44 | estimated72 | ×1.64 |
| LFM2.5-24B-A2B | 24B MoE | community74 | community114 | ×1.54 |
| Muse Glimmer 30B | 30B | estimated6 slow | estimated11 slow | ×1.83 |
| MiniCPM-V 4.7 35B-A3B | 35.2B MoE | estimated52 | estimated54 | ×1.04 |
| Nemotron 3.5 Lightning | 30B MoE | estimated41 | community72 | ×1.76 |
| Gemma 4 31B | 31B | estimated7 slow | estimated13 slow | ×1.86 |
| Gemma 4 26B-A4B | 26B MoE | estimated48 | estimated78 | ×1.62 |
| Raon-1 mini preview | 28.8B MoE | estimated54 | community86 | ×1.59 |
| GLM-4.7-Flash | 31B MoE | estimated45 | estimated73 | ×1.62 |
| North Mini Code 1.0 | 30.5B MoE | community34 | community70 | ×2.06 |
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.
At Apple’s list prices the MacBook Air M5 (24 GB) costs $62 per GB of unified memory and the MacBook Pro M5 Pro (24 GB) $104. On LFM2.5-24B-A2B — the reference model here, which both run — that is $20 and $22 per tok/s of decode speed: the MacBook Air M5 (24 GB) buys more speed per dollar.
The $1,000 premium (67% more) buys +54% decode speed on LFM2.5-24B-A2B.
Bottom line: The MacBook Pro M5 Pro (24 GB): a median 1.9× the speed for $1,000 more.
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.
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 MacBook Pro M5 Pro (24 GB), if the $1,000 premium fits: the LLMCheck index’s figures put it a median 1.9× faster across the 60 shared models with a figure on both; on LFM2.5-24B-A2B, 114 against 74 tok/s (both community runs). That is 307 GB/s of memory bandwidth against 153 GB/s.
Decode speed on Apple Silicon follows memory bandwidth: the MacBook Pro M5 Pro (24 GB) reads memory at 307 GB/s, the MacBook Air M5 (24 GB) at 153 GB/s. The LLMCheck index puts LFM2.5-24B-A2B at 114 tok/s (community run) against 74 tok/s (community run). Across the 60 shared models with a figure on both, the median gain is 1.88x.
Yes. Both fit the same 63 of the 130 models in the LLMCheck index.
It costs $2,499 against $1,499 (Apple list prices, checked 14 Nov 2026; the MacBook Pro M5 Pro (24 GB) price includes 1TB of storage, the MacBook Air M5 (24 GB) price 512GB). For that it gives 114 tok/s (community run) against 74 tok/s (community run) on LFM2.5-24B-A2B. Worth it if you use the extra speed or models daily; the cheaper Mac still runs every model the dearer one does.
On the MacBook Air M5 (24 GB): Qwen 3.6-35B-A3B at ~59 tok/s (estimated). On the MacBook Pro 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.