M4 generation
Local LLMs on the M4 Max (40-core GPU)
The M4 Max (40-core GPU) moves 546 GB/s and takes up to 128 GB of unified memory. That combination runs everything up to Mistral Medium 3.5 at Q4, at roughly 6.3 tokens/sec. Bandwidth sets the speed, memory sets the ceiling, and the tables below give both for every model.
Memory bandwidth
546 GB/s
Unified memory
48, 64, 128 GB
8B model at Q4
~77 tok/s
Found in: MacBook Pro 14/16-inch (2024), Mac Studio (2025). Specifications verified 2026-09-11against Apple’s published figures.
Mac Studio with the M4 Max (40-core GPU) for local LLMs
The Mac Studio is the desktop that carries the M4 Max (40-core GPU), and for local inference it is a different class of machine from a Mac mini. The mini stops at the M4 Pro: 64 GB and 273 GB/s. The Studio with the M4 Max (40-core GPU) goes to 128 GB and 546 GB/s, which is 2x the bandwidth and therefore about that much faster on any model that fits both. At 128 GB it holds Mistral Medium 3.5 at Q4_K_M, which no mini can.
Two things to check before ordering a Studio for this: memory is fixed at purchase, so size it for the largest model you expect to run, not the one you run today, and the price gap to a used RTX 3090 or a DGX Spark is on the hardware comparison. The calculator gives the memory and tokens per second for any model on this chip.
What the M4 Max (40-core GPU) runs, at Q4_K_M
Memory figures include a 3 GB reserve for macOS and an 8K context. Speeds come from a model fitted to our own measured benchmarks; the method and its error bars are on the calculator page.
| Model | Needs | 48 GB | 64 GB | 128 GB |
|---|---|---|---|---|
| Llama 3.2 3B | 8 GB | 140 tok/s | 140 tok/s | 140 tok/s |
| Mistral 7B | 16 GB | 83 tok/s | 83 tok/s | 83 tok/s |
| Qwen 2.5 7B | 16 GB | 80 tok/s | 80 tok/s | 80 tok/s |
| Llama 3.1 8B | 16 GB | 77 tok/s | 77 tok/s | 77 tok/s |
| DeepSeek R1 Distill 8B | 16 GB | 77 tok/s | 77 tok/s | 77 tok/s |
| Qwen 2.5 14B | 16 GB | 46.8 tok/s | 46.8 tok/s | 46.8 tok/s |
| Qwen 2.5 32B | 32 GB | 23.1 tok/s | 23.1 tok/s | 23.1 tok/s |
| Llama 3.3 70B | 56 GB | — | 11.2 tok/s | 11.2 tok/s |
| Qwen 2.5 72B | 56 GB | — | 10.8 tok/s | 10.8 tok/s |
| Mistral Small 4 | 88 GB | — | — | 6.7 tok/s |
| Mistral Large 2 | 96 GB | — | — | 6.5 tok/s |
| Mistral Medium 3.5 | 96 GB | — | — | 6.3 tok/s |
| DeepSeek V4 Flash | 208 GB | — | — | — |
| Llama 3.1 405B | 288 GB | — | — | — |
| DeepSeek V3 | 480 GB | — | — | — |
What it cannot run
Even at 128 GB, these need more unified memory than the M4 Max (40-core GPU) can address at Q4: DeepSeek V4 Flash, Llama 3.1 405B, DeepSeek V3. Dropping the quantization buys a little room but not a generation of it, so the real options are a chip with a higher ceiling or several machines with pooled memory.
M4 Max (40-core GPU) against the M3 Max (40-core GPU)
Bandwidth went from 400 GB/s to 546 GB/s, which is 1.37x, and that ratio carries almost directly into generation speed at the same model and quantization. The memory ceiling went from 128 GB to 128 GB, which is the part that decides whether a model runs at all rather than how fast. The ceiling did not move, so this is a speed upgrade rather than a capability one. If a model did not fit before, it still will not.
Common questions
What is the largest model an M4 Max (40-core GPU) can run?
At Q4_K_M with 128 GB of unified memory, Mistral Medium 3.5 is the largest of the major open models that fits, needing about 96 GB once macOS is accounted for. Anything larger has to drop to a smaller quantization, run across clustered machines, or move to a chip with a higher memory ceiling.
How fast is the M4 Max (40-core GPU) for local inference?
It has 546 GB/s of memory bandwidth, and generation speed on Apple Silicon is set almost entirely by bandwidth divided by the size of the weights. In practice that works out to roughly 77 tokens/sec on an 8B model at Q4 and 23.1 on a 32B, assuming they fit. That is about 1.37x the M3 Max (40-core GPU) at the same model size.
Is a Mac Studio with the M4 Max (40-core GPU) good for local LLMs?
Yes, and it is the reason the Mac Studio exists in this market: it is the only Apple desktop that ships the M4 Max (40-core GPU) with up to 128 GB of unified memory and 546 GB/s of memory bandwidth. A Mac mini tops out at the M4 Pro with 64 GB and 273 GB/s, so the Studio is the step up when a model does not fit in 64 GB or when you want 2x the generation speed on the same model.
How much memory should I order with an M4 Max (40-core GPU)?
Memory decides which models you can run at all, and it cannot be upgraded later, so it is the one specification worth overbuying. M4 Max (40-core GPU) ships in 48, 64, 128 GB. The 48 GB configuration caps you at the small end; 128 GB is what opens up the larger models in the table on this page.
Rent an M4 Max (40-core GPU) instead of buying one
We run this exact chip as a dedicated machine, from $197/mo billed annually or $286/mo billed monthly, with Ollama installed and an OpenAI compatible endpoint already exposed. Same silicon and the same numbers as this page, without the hosting, the static IP, or being your own on call.