Apple M1 vs M4 for local AI: memory, bandwidth, and what actually fits

I'm Matt Kerr, and I build Outlier, a Mac app that runs language models on your own hardware — so I'm an interested party, worth saying up front. This is the hardware note I wish I'd had, and it includes where a PC with a discrete GPU wins.

Unified memory is why a Mac is in this conversation

On a PC, a model has to fit the graphics card's VRAM: 12GB card, 12GB budget, and the system RAM next to it doesn't help. Apple silicon shares one pool between CPU and GPU, which is why MLX — Apple's MIT-licensed array framework — is built on the premise that its arrays live in shared memory.

The M1 has this too. Unified memory shipped in November 2020, so a 16GB M1 holds a model that would otherwise need a 16GB card. The advantage is architectural, not generational.

Capacity and bandwidth are two different limits

Capacity is a wall: the weights fit in RAM or the machine falls back to disk and the experience collapses. Bandwidth is a slope: each token means reading the weights out of memory, so tokens per second scales with read speed.

Apple never published a bandwidth figure for the base M1, but it called M1 Max's 400GB/s nearly six times M1's, and later put M5's 153GB/s at more than double M1's — both imply about 68GB/s. M4 is a documented 120GB/s, a 1.76x ratio. In llama.cpp's community table (LLaMA 7B, Q4_0), M1 generates 14.15 tok/s and base M4 manages 24.11 — 1.70x. Decode is a bandwidth story.

Prefill is compute-bound, so GPU cores show up there instead — 117.96 tok/s on M1 against 885.68 on M4 Max — and that's the wait before the first word appears.

What each configuration actually fits

The "what fits" row uses Outlier's tiers because those RAM minimums are measured rather than guessed.

Two caveats. 16GB is the M1 maximum, not its typical configuration — Apple's spec sheet for the M1 MacBook Air reads "8GB unified memory, Configurable to 16GB," which is why LM Studio tells 8GB owners to stick to smaller models. Chip ceilings aren't machine ceilings either, and in mid-2026 the gap is wide: Apple's own spec pages top the M4 Mac mini at 24GB, the M4 Pro Mac mini at 48GB, and the M4 Max Mac Studio at 64GB, while the MacBook Pro line has moved to M5 entirely. So the 64GB and 128GB in that row are what the silicon supports, not what you can order — 64GB is reachable today only on a Mac Studio, and 128GB only on a used or refurbished M4 Max MacBook Pro. And the throughput figures are community-submitted, one model at one quantization.

The pool is shared, too: macOS and your browser draw from the same RAM the weights need, so usable budget sits below the nameplate. Metal exposes a "recommended max working set size" for this, but I couldn't retrieve Apple's documented fraction, so I won't quote one.

The Neural Engine numbers are the wrong number

Most M1-vs-M4 comparisons lead with 11 TOPS against 38. For local language models that figure is inert. MLX's lead maintainer wrote in the project's own repo that there are no plans to support the ANE "given it is a closed source API," and the request is closed as wontfix. Your tokens come off the GPU on both chips.

M4's 38 TOPS is also widely reported as an INT8 measurement against M1's FP16 figure. I found no Apple page stating either precision, so treat cross-generation TOPS as not directly comparable.

Thermals, price per gigabyte, and the upgrade path that isn't

Local inference is a sustained load, not a burst — a long generation pins the GPU for its whole duration. I have no vendor-published data comparing a fanless Air against an actively cooled mini under that load, so I won't put numbers on it. If you'll generate for hours a day, pick the actively cooled chassis. Both chips do this at laptop power, quietly, on battery — a combination few discrete-GPU laptops sustain at comparable power draw.

Unified memory is part of the chip package and chosen when you order — Apple's spec language is "configurable to." There's no aftermarket upgrade, so build-to-order is the most consequential decision here. Buy memory first.

Apple's store prices as I write this: Mac mini with M4 and 16GB at $799, with M4 Pro and 24GB at $1,599 — about $50 per nameplate gigabyte at the entry point. M1 machines aren't sold new any more (the Air line is M5 only), so an M1 is a used or refurbished buy at prices I can't source. Which raises the currency problem: M5 shipped in October 2025 at 153GB/s, with Apple claiming over 4x M4's peak GPU compute (and over 6x M1's peak GPU compute for AI).

Where a discrete GPU wins, and where Apple silicon does

On raw throughput, a PC with a good discrete GPU is usually faster than a Mac at a similar price, and I'd rather say so than pretend otherwise. Dedicated graphics memory runs at bandwidths no base Apple chip approaches, and CUDA's tooling is deeper than Metal's. If your model fits comfortably in VRAM, buy the card.

Apple's counter isn't speed, it's capacity per dollar and watts per token. A card makes you shrink the model to fit it; unified memory lets you scale the model to the machine — Apple markets M4 Max's 128GB as enough for models of nearly 200 billion parameters. Matching that in cards costs far more and draws far more power.

The M1 gets written off too fast, too. Apple Intelligence still requires only "M1 and later," and LM Studio's minimum is Apple silicon on macOS 14. Apple's Foundation Models framework hands third-party apps a roughly 3B on-device model, free and offline, on any Apple Intelligence-capable Mac, though the weights aren't published. And 14 tok/s on a 7B model is faster than most people read.

What M4 buys is the ceiling, not the speedometer: 16GB to 32GB moves you out of "7-9B only" and into 27B-class territory — a category change, not a percentage. In Outlier's tiers that's Lite 9B versus Core 27B, which scored 98.9% of rubric checks against Claude Opus 4.7 across a 54-prompt head-to-head.

Pick the chip by the model you want to run

You have an 8GB M1: capacity is your wall and tuning won't move it. A 4B model works well — Outlier's Nano is a 2.37GB download, 6GB minimum — and a 27B never will.

You have a 16GB M1: keep it. 4B to 9B models with sensible context lengths are a working local setup today. Upgrade when you want 27B-class quality.

Buying new on a budget: the $799 M4 Mac mini is a fair entry point, but put the build-to-order money into memory — and compare current M5 machines first.

Long documents or codebases: pay for GPU cores. Prefill is where M4 Pro and Max earn their price.

The largest models: 64GB minimum — and no M4 Pro machine Apple currently sells gets there, since the M4 Pro Mac mini stops at 48GB. Today that means a Mac Studio, where M4 Max starts at $2,499 with 36GB and Apple lists 64GB as a build-to-order option on the 40-core-GPU M4 Max, or a used 128GB M4 Max MacBook Pro. Outlier's Plus tier (397B-a17b, 209GB) pages experts off the SSD to hold peak RSS near 11GB — 1.59 tok/s on my M1 Ultra, useful for hard problems and nobody's idea of chat.

Throughput above all, on a model that fits a card: buy the PC. I'd rather you got the right machine than the one I write software for.