Home›Hardware›Mac mini with M6 and 16 GB
Mac mini with M6 and 16 GB
Apple silicon16 GiB153 GB/s5.5 TFLOPS
Once the system takes its share, this machine leaves 13.00 GiB for the model: room for 10 of the 28 models we measure at the reference compression, and the heaviest one that fits is gpt-oss-20b. And how fast does it answer? That’s not down to the chip, but to its 153 GB/s of memory bandwidth.
Left for the model
Estimated
Memory bandwidth
Vendor declared
Models that fit
Measured by Local AI Scope
Videos: Mac mini with M6 and 16 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 | 16 |
| Reserved for the system | −3.00 |
| Left for the model | 13.00 |
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.
153 GB/s — Vendor declared · checked against the manufacturer’s page on 2026-09-22 (Source).
The figure everybody repeats for the M6 is 170 GB/s, and it is not the one on this machine. Apple’s own spec sheet gives 153 GB/s for the two 16 GB configurations and notes the other number in brackets, on the line that offers more memory: «Configurable to: 24GB or 32GB (170GB/s memory bandwidth)». The press release only ever says «up to 170GB/s» — the up to is doing the work. So the cheapest new Mac, the one at $899, reads its memory about 11 percent slower than the same chip with more of it. That gap moves the estimated reading speed below, not what fits: what fits is decided by the 16 GB.
Compute: 5.5 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 | no | 32k |
| 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 | no | 32k |
| qwen3.5-9b | Q4_K_M |
5.29 GiB | yes | yes | yes | 128k |
| gemma4-12b | Q4_K_M |
6.63 GiB | yes | yes | yes | 128k |
| phi-4 | Q4_K_M |
8.43 GiB | yes | — | — | 16k |
| gpt-oss-20b | Q4_K_M |
10.83 GiB | yes | yes | no | 32k |
| mistral-small-24b | Q4_K_M |
13.35 GiB | no | no | no | — |
| qwen3.8-27b | Q4_K_M |
15.33 GiB | no | no | no | — |
| muse-glimmer-30b | Q4_K_M |
15.61 GiB | no | no | no | — |
| qwen3.6-27b | Q4_K_M |
15.66 GiB | no | no | no | — |
| gemma4-26b-a4b | Q4_K_M |
15.78 GiB | no | no | no | — |
| gemma4-31b | Q4_K_M |
17.07 GiB | no | no | no | — |
| qwen3-coder-30b | Q4_K_M |
17.28 GiB | no | no | no | — |
| qwen3.6-35b-a3b | Q4_K_M |
20.61 GiB | no | no | no | — |
| flint-40b | Q4_K_M |
23.61 GiB | no | no | no | — |
| nemotron-3.5-lightning-30b | Q4_K_M |
23.73 GiB | no | no | no | — |
| gpt-oss-120b | Q4_K_M |
58.46 GiB | no | no | no | — |
| 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 | — |
| mistral-large-4 | Q4_K_M |
591.21 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 — 10 of the 28 models measured
- qwen3-1.7b
Q4_K_M— context 32k tokens - qwen3-4b-2507
Q4_K_M— context 32k 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 32k tokens - qwen3.5-9b
Q4_K_M— context 128k tokens - gemma4-12b
Q4_K_M— context 128k tokens - phi-4
Q4_K_M— context 16k tokens - gpt-oss-20b
Q4_K_M— context 32k tokens
Models that do not fit — 18 of the 28 models measured
- mistral-small-24b
Q4_K_M— short by 1.65 GiB - qwen3.8-27b
Q4_K_M— short by 3.26 GiB - muse-glimmer-30b
Q4_K_M— short by 3.41 GiB - qwen3.6-27b
Q4_K_M— short by 3.59 GiB - gemma4-26b-a4b
Q4_K_M— short by 3.73 GiB - gemma4-31b
Q4_K_M— short by 5.83 GiB - qwen3-coder-30b
Q4_K_M— short by 5.33 GiB - qwen3.6-35b-a3b
Q4_K_M— short by 8.37 GiB - flint-40b
Q4_K_M— short by 11.42 GiB - nemotron-3.5-lightning-30b
Q4_K_M— short by 11.43 GiB - gpt-oss-120b
Q4_K_M— short by 46.28 GiB - llama4-scout-17b
Q4_K_M— short by 49.30 GiB - nemotron-3.5-super-120b
Q4_K_M— short by 53.00 GiB - qwen3.8-flash-next
IQ4_XS— short by 75.02 GiB - deepseek-v4-flash
IQ4_XS— short by 115.29 GiB - glm-5.3-flash
Q4_K_M— short by 174.80 GiB - glm-5.2
Q4_K_M— short by 422.12 GiB - mistral-large-4
Q4_K_M— short by 579.37 GiB
Willing to compress a bit more? Then not everything on this list is out of reach. In the 13.00 GiB of unified memory left for the model, mistral-small-24b runs at Q3_K_M (10.69 GiB) with up to 8k tokens of context, and gemma4-26b-a4b runs at Q3_K_M (11.85 GiB) with up to 8k tokens of context. Below the compression in the table a model loses quality, and at Q3_K_M noticeably more; that is why our count sticks to the table.
The machines on either side
- PC with an RTX 4070 12 GB — 11.20 GiB left for the model, 9 / 28 models
- Mac with M4 and 16 GB unified memory — 13.00 GiB left for the model, 10 / 28 models
- Office laptop, CPU only, 16 GB — 13.00 GiB left for the model, 10 / 28 models
- Mac with M4 Pro and 24 GB — 21.00 GiB left for the model, 17 / 28 models
The same machine with different memory
- Mac mini with M6 and 32 GB — 29.00 GiB left for the model, 20 / 28 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.
From $899 (United States), as published on 2026-09-23 (Source). Vendor declared
For once the starting price is this machine’s price. The $899 Apple quotes for the Mac mini with M6 is the 16 GB configuration, with 256 GB of storage, and it is also the lowest price in the whole Mac mini family. The other 16 GB model, with 512 GB of storage, is $1,099. Apple publishes no price in euros: the figure is in US dollars.
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».


