Mac mini M4

having a 64GB mac mini m4 pro the last few years with some increasingly capable usefulness has kept me interested in this stuff in a way that using a paid platform wouldn't have. Similar to running K8s in a homelab, something about interacting with the hardware makes it more engaging/interesting, for me at least. In general, I'm a big believer in doing more with fewer resources, within reason, and think having local setups really helps me be mindful with what's happening under the hood with these systems and managing context efficiently to get high quality results.

[...] A Mac Mini M4 Pro from last year and an older M1 MacBook. I separate my work and private usage because of all the security software my employer forces on the machine. [...] If not for the M1 I would definitely have spend money for a MacBook Air or a used older laptop. [...] Used would be the way to go here but I love the fact that there is finally a good value entry level machine that also looks fun.

[...] I'm using a macmini m4 16GB and so far my prefered model is Qwen3-4B-Instruct-2507-Q4KM although a bit chat but my test with Qwen3.5-4B-UD-Q4KXL shows it's a lot more chat, I'm basically using it in chat mode for basic man style questions. [...] I'm floowing this topic heavilly for the last 3 months and I see more confusion than clarification. [...]

[...] It is so incredibly unintuitive in every way for window management and keyboard shortcuts and everything in between. My Mac Mini M4 is for building the Mac/iOS apps, other than that it's useless as a daily driver. [...]

I actually have a Mac Mini M4 Pro with 48G. [...]

It’s not because you didn’t find use cases for local LLMs that there are none. I use local LLMs on my Mac Mini M4 Pro with 48G to review text messages tone, act as a text correction tool, act as a code review tool, to do code agent work, generate code snippets, etc Gemma 4 26B A4B gives me steady 20 tps.

[...] macOS Tahoe 26.6.1, Mac mini M4 Pro (14 core, 20 graphics cores) 64GB RAM. [...] It actually output just a straight SVG file of an owl (not a bad owl either!), whereas Qwen 3.8 27B spent a zillion times longer gold-plating everything and output HTML+JS+SVG with interactive animation, sound, etc., etc.

[...] Mac mini M4 Pro (cores: 10P/4E/20G) 64GB Tahoe 26.6 LM Studio 0.4.20+1 Qwen3.6-35B-A3B-MLX-4bit: 78.81 tok/s, TTFT 0.93s (but note Qwen 35B is really chattery and outputs 3,451 words of thinking for 65s first) Qwen3.6-27B-MLX-4bit: 14.65 tok/s, TTFT 0.76s (Qwen 27B output 3,027 words of thinking for 361s first, spinning up the fans) gemma-4-26B-A4B-it-QAT-MLX-4bit: 64.93 tok/s, TTFT 0.44s (Gemma 26B is much more on-task, thinking with 591 words for 15.62s first) gemma-4-31B-it-QAT-GGUF Q40: 12.25 tok/s, TTFT 1.65s (Gemma 31B thought with 404 words for 51.55s)

MacBook Pro M5 128GB RAM 614 GB/s of memory bandwidth MacMini M4 with 64GB of RAM 273 GB/s of memory bandwidth (also only currently available with 48GB) When it comes to inference speed, you want your model to fit in memory, and then to have as much memory bandwidth as possible. In this case a hypothetical Mini with 1TB of memory would still be over 2x slower with 27-35B models. And FWIW I have an M4 Max MBP 128GB that I keep on a Roost laptop stand, with a separate keyboard/mouse/video. [...]

[...] I just purchased a Mac Mini M4 Pro 64GB for $3k - 2nd hand of course. I am not a hater of Nvidia and I am planning on building a workstation based on RTX cards. You clearly do not seem to understand how convenient the MacMini actually IS - the form factor, how quiet it is, how durable it is, how well it integrates with other Macs, how well it works as a bridge to a personal agent like Hermes (integration with iMessage, Calendar, Reminders, iCloud, etc). I am pretty sure I know a thing or two about computing, I have been in the trenches for many, many years and I have had machines of all kinds, shapes and colors. [...]

[...] If you want to run Qwen3.6 27B / 35B at its best, get a MacMini M4 with 64GB of RAM and put it in the basement - or at least a few meters from your desk. [...]

[...] It’s hosted on an Orbstack VM on a Mac Mini M4 on my local Tailscale network and the UI is incredibly snappy and quick to browse. [...]

[...] The 27B is the smarter, more reliable one - but it is slower. [...] What excites me more: I run the 35B model on a MacMini M4 with 64GB RAM. [...]

My Mac Mini M4 has a distasteful smell when I pin in with AI prompts. [...]

I bought a Mac mini m4 before openclaw to use as a music production machine, when it turned out not to work out I tried setting up openclaw on it after hearing all the noise, but that turned out not to work out either. [...] I use it as a Tailscale + ssh + tmux + Claude code machine, which gives me an always on Claude code environment with persistent sessions. I ssh from my phone using termius and from my laptop through ssh, and I can even access my projects through Tailscale with hot reloading for the most part, no deploy needed. [...]

[...] I am starting to use Gemma 4:e4b as my daily driver for simple commands it definitely knows, things that are too simple to use ChatGPT for. [...]

I run a few servers at home (Mac Mini M4 + Raspberry Pi) and got tired of the same 3 AM routine — SSH in, check what crashed, restart a container, go back to sleep. [...]

In case someone would like to know what these are like on this hardware, I tested Gemma 4 32b (the 20 GB model, the largest Gemma model Google published) and Gemma 4 gemma4:e4b (the 10 GB model) on this exact setup (Mac Mini M4 with 24 GB of RAM using Ollama), I livestreamed it: The 10 GB model is super speedy, loading in a few seconds and giving responses almost instantly. [...] I also had each of them complete a difficult coding task, they both got it correct but the 20 GB model was much slower. It's a bit too slow to use on this setup day to day, plus it would take almost all the memory. The 10 GB model could fit comfortably on a Mac Mini 24 GB with plenty of RAM left for everything else, and it seems like you can use it for small-size useful coding tasks.

my mac mini m4 is getting to be a good substitute for claude for a lot of use cases. LM Studio + qwen3.5, tailscale, and an opencode CLI harness. It doesn't do well with super long context or complexity but it has gotten production quality code out for me this week (with some fairly detailed instructions/background).

I'm running a local voice agent on a Mac Mini M4. [...]

[...] I've been running it for 7 days on a Mac Mini M4 managing two actual businesses. Setup: Mac Mini M4 16GB from Costco ($640 after CA tax), running 24/7. [...] It found an SMS chatbot that had been broken for 10 months (legacy app version issue in my automation platform). [...] It remembers multi-day project context, references past decisions, and builds on previous work. [...] When writing marketing copy, it invented $150 in freelancing revenue that never happened and got the hardware price breakdown wrong. [...]

my PC always comes back to the login screen immediately after I manually use "sleep" from the power menu. My Mac Mini M4 is on its way. [...]

Compared to both Windows 10 and macOS 26 (my desktop computer is a Mac Mini M4 and I really regret updating it to Tahoe). Linux obviously has its strengths, so I have a dual boot with the latest Fedora, but I almost always end up using W11, even for personal use.

I bought an Apple Mac Mini M4 recently. [...] Until you start upgrading it, then the price hikes are just pure extortion. [...]

I bought a Mac mini M4 simply because it was very cheap and the M4 chip offers great performance. [...] It runs macOS, but I have no particular interest in the operating system, nor do I own any other Apple hardware. (So no synergies.) It is alright (and better than Win11) but the preinstalled software does not even properly update without an Apple account. [...]

[...] Mac Mini M4 from Costco ($640), running Opus 4.5 via Claude Max. [...] - It found and fixed an SMS chatbot that had been broken for 10 months in my CRM. [...] It references decisions from days ago and builds on previous work. [...] For solo founders willing to invest setup time: worth it. [...]

Right now I'm running a setup with Fedora on my work machine, CachyOS on my laptop, Windows on my home battlestation gaming rig and a Mac Mini M4 I bought for a educational discount. [...] Chances are, if I have another drive (which is slowing going into the unobtainium territory, just like RAM) But, long as I settled that dust, I will bring another PC back to my home. [...]

[...] If you're buying a Mac mini, get the cheapest one and buy this drive. [...] Also, I still cannot fathom why people insist that the base storage for Mac mini M4 is fine. [...] My phone has more...

Have a macmini m4 32G, not the pro version, previously everytime I tried local LLM is a bit disappointing, and I finally decide to not waste time and perhaps in the future invest a better hardware to server more modern and dense model I am curious is what is the 80% request served by this setup, I was using it for OpenClaw which run serveral cron jobs that discover stuffs over the wide internet, check my support system's unanswered tickets, browser X and some social media for me to filter the valued ones(though I have to say even with GPT 5.6 sol, the quality is low for the timeline X sent to me) Btw, Tailscale is quite cool and did a good job, I was using it to serve the local LLM and connct the openclaw on a Linux Machine to it.

[...] Yesterday it was $799 for the base Mac Mini M4, a $200 increase from the original MSRP before June’s price hikes. [...] I understand why; the prices of DIMMs, GPUs, and SSDs have also skyrocketed. But $899 for a base Mac Mini is painful, even if the alternatives on the current market are also painfully expensive.

There's some mention of Apple silicon here but it's worth expanding upon. [...] Here are some examples: - GMKTek EVO-X2: 120GB/s reads, 212GB/s writes - NVidia DGX Spark 273GB/s - Mac Mini M4 120GB/s but only $600+ - Mac Mini w/ M4 Pro 273GB/s ($2199 for 64GB) - Mac Studio M4 Max 410GB/s ($3500 for 128GB) - Mac Studio M3 Ultra 819GB/s ($5500 for 96GB) - Macbook Pro 16" with M5 Pro 64GB 307GB/s ($3300) - Macbook Pro 16" with M5 Max 128GB 460GB/s ($5399) Sadly, Apple discontinued the 512GB Mac Studio. [...] I suspect that prices will be a lot higher given the RAM prices but we'll see.

Ollama is slower I've benchmarked this on an actual Mac Mini M4 with 24 GB of RAM, and averaged 24.4 t/s on Ollama and 19.45 t/s on LM Studio for the same 10 GB model (gemma4:e4b), a difference which was repeated across three runs and with both models warmed up beforehand. [...]

Apple is getting everything wrong these days. I am so disappointed after buying a Mac mini M4 last year how everything is sandboxed and behind insane numbers of security layers. I will be moving to Linux as soon as my wallet allows it.

@ambientspace I got a Mac mini M4 a year ago, I hope it is able to have that long of a useful life.

If yall need a new computer I just have to say the $600 Mac mini m4 I have been using for a few months now is legit the fastest computer I have owned. Crazy value. I do a lot of Unity, blender, photoshop, premiere, Godot

[...] I bought a Mac Mini M4 Christmas 2024. [...]

I bought a Mac mini m4 last year to compile UE5 for iOS/iPad. [...] It would be fun to think that the Mac Mini unlocks some sweet spot of performance but I’m seeing responses from the Clawdbot developers showing how you can run Clawdbot on AWS’ free tier so guess the mini is not necessary / just a fantasy.

I run Qwen 3.8 27B just fine on my Mac mini M4 24GB. I use Unsloth's Q3 XXS with 128k context. It successfully completes long horizon tasks with OpenCode.

[...] Mac Mini M4 Pro with 48G RAM as a headless llama.cpp server. [...]

That’s great advice the main distros tend to have tons of support for much longer and easier to maintain I’m sure. I currently have a Mac mini m4 so I’m thinking a similar sized box with an AMD setup inside, those small mini PCs.

I currently just use a Mac Mini M4 with cursor. [...]

[...] But I also have a MacMini M4 Pro 64GB. [...]

I recently bought a Mac mini M4 16 GB - mostly to run Immich. [...] After a lot of researched I was quite surprised that the mac was the cheapest option. [...]

It's amazing how far this emulator has come over the past few years. It runs so well on my Mac Mini M4 Pro system that it has effectively replaced my real 500 MHz Celeron rig for all but the most demanding activities.

Anecdata: Ordered my Mac mini M4 Pro (48GB) on April 1. [...]

openclaw fills the gap left by Siri and was built with tight integration with Apple ecosystem. [...] i would say a majority of users are tech and non tech roles, who (1) have an iPhone with all their contacts and data on iCloud (2) have a macbook at work and use macOS daily (3) use ChatGPT or Claude daily and trust it with their personal data (4) aren't familiar with Linux or a VPS and don't trust themselves with setting it up through the terminal (5) feel more at ease with a "a second macOS that i can debug visually on my monitor at home" rather than a remote linux VPS you could still rent a mac mini but cloud providers will ask you $119 a month for a Mac mini M4 with 16GB of RAM. $599 is unbelievably cheap for a second computer with which you can do anything you can do on your usual Macbook

There’s a lot of commentary to the effect that the Mac hardware is good, but the software is somehow terrible. Speaking as someone who first used a Mac Plus, graduated to an SE/30, and is now on a Mac mini m4 pro… I can remember when Macintosh was widely held to be an acronym for Most Applications Crash, If Not, The Operating System Hangs. The software has always been terrible, until you try the other guys’ stuff. [...]

[...] I spent a weekend building an alternative using Blink (OSS agent orchestration), Tailscale (WireGuard-based private networking), and a Mac Mini M4. [...]

[...] Like I ran a test on R1 (the smallest version) vs Perplexity Pro and shockingly got better answers running on base spec Mac Mini M4. [...]

[...] I bought the cheapest mac mini M4 on sale, put it in basement and started working on some cli+daemon to help me automate all things around it. [...]