Home›Hardware›Mac with M4 Max and 64 GB
Mac with M4 Max and 64 GB
Apple silicon64 GiB546 GB/s18.4 TFLOPS
The manufacturer no longer sells this machine new. It stays in this hub because the arithmetic still answers the question if you are looking at a second-hand unit or comparing it with what is on sale today; the store no longer lists any new machine with this chip. Which one replaces it, and at what price, is in the price block further down.
Once the system takes its share, this machine leaves 61.00 GiB for the model: room for 20 of the 26 models we measure at the reference compression, and the heaviest one that fits is gpt-oss-120b. And how fast does it answer? That’s not down to the chip, but to its 546 GB/s of memory bandwidth.
Left for the model
Estimated
Memory bandwidth
Vendor declared
Models that fit
Measured by Local AI Scope
Videos: Mac with M4 Max and 64 GB 3
The best walk-throughs we found. Press play and it opens right here.
The videos live on YouTube, and nothing loads from there until you press play (no-cookie mode). The thumbnail is served by us.
The memory you can actually use
Unified memory is shared with the operating system and everything you have open. The reserve here is deliberately conservative; you can change it in the tool.
| Memory | GiB |
|---|---|
| Memory on the box | 64 |
| Reserved for the system | −3.00 |
| Left for the model | 61.00 |
Memory bandwidth
Two different limits, and they are easy to mix up. While the model is writing its answer, bandwidth rules: every token means reading the weights it uses again — all of them in a dense model; in a mixture of experts, the shared layers plus only the active experts — so tokens per second is roughly bandwidth divided by that amount. While the model is reading your document, compute rules: the whole input is processed at once. That is why a laptop with no GPU can take minutes before the first word appears and then type at a tolerable pace.
546 GB/s — Vendor declared · checked against the manufacturer’s page on 2026-08-25 (Source).
There are two M4 Max chips. The 546 GB/s figure is the 16-core CPU / 40-core GPU variant, which is the only one sold with 64 GB; the 14-core variant runs at 410 GB/s.
Compute: 18.4 TFLOPS (estimate for this class of machine) — Estimated · the manufacturer does not publish this figure at all; ours is a conservative estimate, not a specification. The figures in this line do not all come from the same measure across machines, because each manufacturer publishes a different one. Compare them between machines only with that in mind.
Which models fit here, and which do not
Fitting means three things at once fit in the memory left over: the model file, its context memory, and the runtime’s working headroom. Context memory is computed from each model’s declared attention pattern layer by layer, not from the generic formula — which is why several models fit here that the generic formula would rule out.
| Model | Compression shown | Model size | 8k | 32k | 128k | Largest context that fits |
|---|---|---|---|---|---|---|
| qwen3-1.7b | Q4_K_M |
1.03 GiB | yes | yes | — | 32k |
| qwen3-4b-2507 | Q4_K_M |
2.33 GiB | yes | yes | yes | 256k |
| gemma4-e2b | Q4_K_M |
2.89 GiB | yes | yes | yes | 128k |
| gemma4-e4b | Q4_K_M |
4.63 GiB | yes | yes | yes | 128k |
| qwen3-8b | Q4_K_M |
4.68 GiB | yes | yes | — | 32k |
| granite-4.2-8b | Q4_K_M |
4.98 GiB | yes | yes | yes | 128k |
| qwen3.5-9b | Q4_K_M |
5.29 GiB | yes | yes | yes | 256k |
| gemma4-12b | Q4_K_M |
6.63 GiB | yes | yes | yes | 256k |
| gpt-oss-20b | Q4_K_M |
10.83 GiB | yes | yes | yes | 128k |
| mistral-small-24b | Q4_K_M |
13.35 GiB | yes | yes | yes | 128k |
| qwen3.8-27b | Q4_K_M |
15.33 GiB | yes | yes | yes | 256k |
| muse-glimmer-30b | Q4_K_M |
15.61 GiB | yes | yes | yes | 128k |
| qwen3.6-27b | Q4_K_M |
15.66 GiB | yes | yes | yes | 256k |
| gemma4-26b-a4b | Q4_K_M |
15.78 GiB | yes | yes | yes | 256k |
| gemma4-31b | Q4_K_M |
17.07 GiB | yes | yes | yes | 256k |
| qwen3-coder-30b | Q4_K_M |
17.28 GiB | yes | yes | yes | 256k |
| qwen3.6-35b-a3b | Q4_K_M |
20.61 GiB | yes | yes | yes | 256k |
| flint-40b | Q4_K_M |
23.61 GiB | yes | yes | yes | 256k |
| nemotron-3.5-lightning-30b | Q4_K_M |
23.73 GiB | yes | yes | yes | 256k |
| gpt-oss-120b | Q4_K_M |
58.46 GiB | yes | yes | no | 32k |
| llama4-scout-17b | Q4_K_M |
60.87 GiB | no | no | no | — |
| nemotron-3.5-super-120b | Q4_K_M |
65.29 GiB | no | no | no | — |
| qwen3.8-flash-next | IQ4_XS |
87.25 GiB | no | no | no | — |
| deepseek-v4-flash | IQ4_XS |
127.28 GiB | no | no | no | — |
| glm-5.3-flash | Q4_K_M |
187.04 GiB | no | no | no | — |
| glm-5.2 | Q4_K_M |
433.83 GiB | no | no | no | — |
Sizes are the real published files at the reference compression, one step per row: Q4_K_M where the author publishes it, the nearest neighbour where they do not. Every row states which one it is showing. Q4_K_M is our quality floor: below it the loss is audible in the answers. A model that would only fit here at a harsher compression is listed as not fitting, on purpose. A dash in a context column means the model itself does not offer that context, so there is nothing to fit.
Models that fit — 20 of the 26 models measured
- qwen3-1.7b
Q4_K_M— context 32k tokens - qwen3-4b-2507
Q4_K_M— context 256k tokens - gemma4-e2b
Q4_K_M— context 128k tokens - gemma4-e4b
Q4_K_M— context 128k tokens - qwen3-8b
Q4_K_M— context 32k tokens - granite-4.2-8b
Q4_K_M— context 128k tokens - qwen3.5-9b
Q4_K_M— context 256k tokens - gemma4-12b
Q4_K_M— context 256k tokens - gpt-oss-20b
Q4_K_M— context 128k tokens - mistral-small-24b
Q4_K_M— context 128k tokens - qwen3.8-27b
Q4_K_M— context 256k tokens - muse-glimmer-30b
Q4_K_M— context 128k tokens - qwen3.6-27b
Q4_K_M— context 256k tokens - gemma4-26b-a4b
Q4_K_M— context 256k tokens - gemma4-31b
Q4_K_M— context 256k tokens - qwen3-coder-30b
Q4_K_M— context 256k tokens - qwen3.6-35b-a3b
Q4_K_M— context 256k tokens - flint-40b
Q4_K_M— context 256k tokens - nemotron-3.5-lightning-30b
Q4_K_M— context 256k tokens - gpt-oss-120b
Q4_K_M— context 32k tokens
Models that do not fit — 6 of the 26 models measured
- llama4-scout-17b
Q4_K_M— short by 1.30 GiB - nemotron-3.5-super-120b
Q4_K_M— short by 5.00 GiB - qwen3.8-flash-next
IQ4_XS— short by 27.02 GiB - deepseek-v4-flash
IQ4_XS— short by 67.29 GiB - glm-5.3-flash
Q4_K_M— short by 126.80 GiB - glm-5.2
Q4_K_M— short by 374.12 GiB
Willing to compress a bit more? Then not everything on this list is out of reach. In the 61.00 GiB of unified memory left for the model, llama4-scout-17b runs at Q4_K_S (57.23 GiB) with up to 16k tokens of context. Below the compression in the table a model loses quality; that is why our count sticks to the table.
The machines on either side
- Mini-PC with an NPU and 32 GB LPDDR5X — 29.00 GiB left for the model, 19 / 26 models
- Server with 2× RTX 3090 (48 GB) — 47.20 GiB left for the model, 19 / 26 models
- Mac mini with M5 Pro and 64 GB — 61.00 GiB left for the model, 20 / 26 models
- Xiaomi AI Cube, 80 GB — engineering prototype — 77.00 GiB left for the model, 22 / 26 models
Price and availability
What a machine costs decides as much as what fits inside it, so the price belongs on this page. What follows is only what the manufacturer publishes, with the market it applies to and the day it was read.
There is no price: this row is a class of machine, not a single product with a price list.
Apple no longer sells any new Mac with an M4 Max: as of 19 September 2026 the store offers M5 Max and M5 Ultra in the Mac Studio, and M5, M5 Pro and M5 Max in the MacBook Pro. There is no current manufacturer price for this class, and none for the 40-core-GPU variant with 64 GB this sheet describes; the machine that replaces it is the Mac Studio with M5 Max, from $2,499 in its 36 GB base configuration.
What we earn on this page
Nothing, today. There is no affiliate link on this page and no commercial agreement behind any figure on it. If a buying link ever appears here, it will be marked as such and the commission declared in this same block. Two rules do not change on that day: the ranking on this site is computed before commercial availability is applied, and «best» never means «pays most».