The stuff Hacker News actually recommends.

Laptops · Apple MacBook Pro

Apple MacBook Pro M5 Max

26owners with an opinion
50%of verdicts positive
10/10positive/negative since 2024
0happy after 3+ years

Praised for performance and portability; criticized for noise and value.

What owners wrote

Doesn’t like it
It's not just the LLM costs, to keep your agents busy you need to move them of your workstation onto a server/cloud. I currently have about 16 claude code agents working on different bugs, uses so much resources that my macbook pro m5 max becomes slow to respond. Using cloud session would free up my macbook for other work. Anthropic recently handed out free cloud resources (it's still free, guess they want you to get used to the fact that cloud is not free). I went through $250 cloud budget in less than 2 days. Feels almost as expensive as LLM calls.
Doesn’t like it
I just bought a portable keyboard for my iPhone - coupled with a SSH client, its quite a useful combo these days. I had to prove the OP wrong though; my M1 Max's keyboard died this year, and I had to upgrade to the M5 max this season, after the hikes. I kissed 9k EUR goodbye for something not much better functionally than the M1 Max it replaced, bought for 3.4k Canadian dollars in the wonderful 2021 (that was barely over 3200 EUR back then).
Neutral
I had a Lenovo thinkpad with OLED before switching to a MacBook Pro (first M1 Max, now M5 max). I don’t really mis the OLED display, it’s not that big of a difference (according to my 55 year old eyes…) the thinkpad also had a touchscreen, never used it, only by mistake. I would not pay extra for a touchscreen or OLED on a laptop. The photos on the apple website are not convincing, playing a keyboard on a vertical screen looks very uncomfortable. Also don’t understand the iPhone duo, I’d rather have a normal iPhone and an iPad Air. Cheaper, and better for mobile use and for couch media consumption.
Doesn’t like it
Ornith 1.5 35B MoE is very close in most benchmarks, but runs at 100 tk/s where Qwen3.8 27B runs at 30 tk/s (MBP M5 Max 48GB). It's now my go-to model for quick inquiries. Ornith 1.0 had problems with world knowledge, but 1.5 seems very solid on that front. I'll be running some agentic tests today. Ornith 1.5 35B is so fast that my CPU doesn't even have time to heat up, where Qwen3.8 would turn my laptop into a toaster within a few minutes. I hope agentic tasks will hold up!
Doesn’t like it
I was in the same situation, I used maxed out 15'' M3 Max MacBook Pro docked to Studio Display closed on vertical stand behind the screen. It was fine for office work, but running local LLMs would definitely overheat it. The battery started degrading purely due to heat issues. And it was audible as well. I decided to get Mac Studio M4 Max, also all maxed out config and the cooling is so much better that I can run local LLMs like Gemma 3/4, gpt-oss 120b all day long without any heat issues or any audible fan noise. So for my use case it was the right decision. I subsequently added 15'' M5 Max MacBook Pro all maxed out to my collection and even though it is slightly faster on LLM inference (I get 100 tokens/s with Gemma 4 27b model), you just can't run LLMs longer than a few minutes. It starts overheating and gets really loud.
Likes it
Your statement is not really true any more. I have an old M1 Max with 32GB that runs inference models fine, especially those using MLX. Dedicated graphics cards are faster but not to the point that it matters. That’s a six year old machine. My newer machine M5 max 128GB will far outperform your typical 32GB gaming card once the model exceeds memory. To even get close to that on a dedicated graphics card you are paying upwards of $20K. That said, models are getting smaller and faster which allows me to run multiple different models with ease. [edit] Just checked the 5 models I use take up 57GB when all loaded at the same time.
Likes it
Tested the model briefly with my usual eval: a couple of questions on general knowledge most small models often get wrong, then write a fully-featured todo list app in JS, then rewrite the same app in Rust with Tauri. Granted, most models are well trained on basic todo apps, but it gives me an idea of the basic SWE capabilities I can build on. As far as I'm concerned, if it can successfully setup a local git repo, write a todo list app skeleton that works, I can work with it. SWE: model is strong for its size. It one-shotted the Web app, had no bug. The Rust rewrite only had one bug (reordering didn't work immediately - fixed in one prompt). Committed locally then pushed to my GitHub ( https://github.com/DexterLagan/RusTODO ). Can't complain. If it can do that reliably, I can use it to make whatever I need. General knowledge: I usually ask 2 questions many small models get wrong: summarize Operation Trojan Horse by John Keel, give publication year. Summarize the Ariel school incident of 1994. Qwen3.8 got the first question right, along correct publication year, gave glorious detail on Keel's theory, but got the second wrong. It thought that school was located in the USA. Ah well. Performance on an admittedly overpowered laptop: 15 tokens/s in power save mode on this MacBook M5 Max 48GB, and 30 in performance mode. Perfectly usable for local coding through OpenCode. Verdict: very nice local and free backup to my usual GPT/Claude/DeepSeek for code. Good for Web searches via Bra…
Recommends it
PSA: Fast RAM isn't going to be getting cheaper anytime soon. Acquiring inference hardware is a really good way to own an appreciating hard asset. Learning how to use it and cool it is a hacker's journey worth taking. My 4090 I bought in late 2022 for $1600 is selling for a cool $3,489.95 right now, and going strong under nominal use. My DRR5 has tripled in value, my nvmes almost doubled. I grabbed a 128GB M5 Max MacBook Pro when they were still available and told all my friends to buy at least one. With that and a base M4 Studio 36GB, HuggingFace rates that hardware as: > Amazing! You have a total of 128.94 TFLOPS of computing power. 71.3% percentile on scale of "GPU Poor" to "GPU Rich" The way I see it, these are amazing machines that the richest folks are hovering up. I think they should be in the hands of regular people as much as possible. They depend on an incredibly global, increasingly fragile supply chain. If the become impossible to produce, their value would increase tremendously. I think they will become really valuable to you to use the tokens directly, but if that isn't the case, they can be rented out or resold. Please don't just buy any hold. Let's try to get as many people that can use them for decent things that help humans. For example: https://spectrum.ieee.org/small-language-models-ai-pharmaceu...
Likes it
There is no socketable Unified Memory platform. The entire point of this SoC is that it has Unified Memory. The Framework Desktop has a Mini-ITX board, but you MUST use a solderable SoC with HBM stacked memory to get a Unified Memory outcome. For local AI workloads, that's the only part that matters, which is the entire point of wanting 192GB of RAM available on an APU. I like the repairability and modularity of my Framework 13 laptop, and I still bought a maxed out MBP M5 Max because for local LLM, unified memory is all that matters.
Neutral
Deleted earlier, didn't see you post, pasting here: /* Just started testing with the gguf (with gpu offload, m5 max 128gb), q4_k_m, running seemingly well. Speed is initially slightly faster than antirez/ds4 - decode tok/s in the 30s, prefill ~400-ish. Expected, given the slightly smaller size. Looks to be working fine, but too early to tell. Definitely likes to "think". */ Anyways, guessing that discord might be focusing on the nvfp4 stuff. I've noticed spelling mistakes in the thinking traces, tool calls have been fine so far.
Neutral
I've been using Qwen 3.6 27B with LMStudio, and I was pleasantly surprised with it, although it was a little slow. I found mtplx last night, and it really wasn't an exaggeration to say that it ran the model 2-3x faster which was super impressive. I'm trying to move to local models as much as I can, and I'm finding that it's becoming more and more practical. Admittedly this is on a $6000 dollar laptop (M5 Max Macbook with the specs maxxed out), so the hardware is still a bit out of reach for most people (the AI industry isn't exactly helping here..), but I'm getting the impression that the future is going to be smaller models with more focused training running locally. The danger of giving all your data to these cloud providers just seems too big to me, and I think they're going to start charging insane amounts when they need to show a profit.
Doesn’t like it
I’ve got a 128gb m5 max mbp and two sparks. For my real-world use cases, a single spark running DS4 Flash will have fully responded by the time my Mac has even started generating tokens. I figured I’d have more generation heavy work when I also bought the Mac, but it has done very little work running LLMs since I got the first Spark. I mostly run them clustered for DS4 and am quite happy with the performance, and the cost isn’t that much more for two than the MBP while giving me double the unified memory. I’ll probably pick up a third to run multiple smaller models. I don’t understand why people would buy a halo over a spark at comparable prices, particularly because if you want to cluster, the cx7 be beats the shit out of them when it comes to latency and throughput
Likes it
If your workflow benefits from the speed it quickly pays for itself when factoring in developer salaries here in the US. I recently switched companies and they bought me an M5 Max 128GB as my dev machine. Builds and local test runs are 3 times faster than the Windows laptop option. The machine will pay for itself just based on that within 3 months. I can spin up a local kubernetes cluster and do full integration tests while I am working on other things as well. It isn’t a strictly Mac vs Windows thing though. It looks like the culprit is the MDM software on the Windows machines is just crazy slow and constantly getting in the way. If I was paid less it would definitely make less sense for the company to pay for this machine.
Likes it
They might add it as a surcharge the way Ubiquiti is doing it. I recently bought a bunch of stuff and it all comes with a memory or tariff surcharge that is annoying but it's hard to argue it. Also we know that it's coming soon, that's why Cook is running cover for the new CEO. They don't want the new CEO to be the one taking the fall on higher prices, so before September 1 will be my guess. Thank God I made the right decision and I bought a max'ed out Macbook Pro 5 Max with 128 GB of memory a couple of months ago. I think prices will continue to keep going up.
Doesn’t like it
I love running two models locally: qwen3.6 27B 8bit (dense) and qwen3.6 35B 4bit (MoE). The 27B is the smarter, more reliable one - but it is slower. The 35B is faster, still very smart but below 27B, a bit less reliable. The reason is the MoE - Mixture of Experts architecture, which only activates a subset of parameters, making the model much much faster. I run the 27B on a MacBook Pro M5 Max + 40 GPU cores + 128GB RAM (well, on this beast I can have 27B + 35B in memory at the same time with headroom for all the other stuff). But because this is a laptop, it is not possible to run local LLMs all the time - it just gets too hot and too loud. What excites me more: I run the 35B model on a MacMini M4 with 64GB RAM. It is fast, it gets a lot of work done (e.g. it scans, extracts and classifies my emails, it watches the mailbox all the time and does work). I also use it as my private Hermes assistant ("when is the next Starship launch?", "who is playing today at the World Cup? Give me some trivia"). Next step I am planning is a RTX Pro 6000 Blackwell workstation I can put in my basement. I want to run qwen really fast, with multiple threads / prompts / agents at once. And MAYBE if the budget allows, a 2x RTX Pro 6000 setup in order to run DeepSeek v4 flash on it (to run research on it).
Doesn’t like it
In the last year, I have bought an M3 Ultra Mac Studio with 512 GB, a Macbook Pro M5 MAX with 128 GB and an RTX 6000 Pro. I have spent around $25k so far, not including electricity. I figured worst case scenario I can sell them in the next year and only take a haircut as opposed to losing my entire investment. In comparison to just spending for tokens, the tokens would have been much cheaper and much much faster. I've been running against Gemma4:31b, Qwen3.5 and 3.6, and getting local LLMs to solve AMC 8/10 math questions and it's about 10-100x slower than just doing it online. When I tried it with ChatGPT late last year, it took about one night and $25 to solve about 1000 questions. Using my RTX 6000 and M3 Ultra and Gemma4:31b on both, it answered about 40 questions in 7 hours and I haven't checked how good the answer is yet. At 800 watts (600 for RTX and 200 for M3 Ultra) and running for 7 hours, it solved around 40 questions. At the very least I'm going to try to sell my M3 Ultra if I can find a reliable place to sell it without getting ripped off by scammers.
Likes it
You can only run heavily quantized models on all 3/4/5 rtx gpus (with 32gb or less vram) - and you probably want moe versions like Qwen 35b for this to run at speed somewhat comparable to Claude. It’s still not there to be honest but getting there. Personally I mess around with llama.cpp on m5 max with 128gb - it’s a decent setup to try various medium sized things, and runs llms surprisingly well without quantization, at least the moe models.
Neutral
With that you are taking a significant performance penalty and become severely I/O bottlenecked. I've been able to stream Qwen3.5-397B-A17B from my M5 Max (12 GB/s SSD Read) using the Flash MoE technique at the brisk pace of 10 tokens per second. As tokens are generated different experts need to be consulted resulting in a lot of I/O churn. So while feasible it's only great for batch jobs not interactive usage.