Can’t you guys just read a book and take a nap?
Running local LLMs offline on a ten-hour flight
11–20 of 112 posts
Re: Running local LLMs offline on a ten-hour flight
#12This has been exactly my experience too. I've tried multiple harnesses (pi, claude code, codex) with multiple variants of qwen3.6 and gemma4 driven by both o mlx and ollama - and every single time I try to do anything meaningful I end up in a loop. On a 64GB Macbook Pro M3 Max. I really don't know what the hell people are doing locally, and suspect a lot of the hype around running these models locally is bullshit. Su…
You need to set sampling parameters for the llm. Had the same issue with Qwen3.5 when i first started. You can grab them off the model card page usually. From Qwen3.6 page: Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0 Thinking mode for precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalt…
Yes, have tried all of these (as per the docs). Have you actually tried these? Because I have tried all 3 configurations with agentic coding that you mentioned and have the same result - loops.
Re: Running local LLMs offline on a ten-hour flight
#13Can’t you guys just read a book and take a nap?
I suppose the ones that do, wouldn't consider such a turn of events postworthy.
Re: Running local LLMs offline on a ten-hour flight
#14This has been exactly my experience too. I've tried multiple harnesses (pi, claude code, codex) with multiple variants of qwen3.6 and gemma4 driven by both o mlx and ollama - and every single time I try to do anything meaningful I end up in a loop. On a 64GB Macbook Pro M3 Max. I really don't know what the hell people are doing locally, and suspect a lot of the hype around running these models locally is bullshit. Su…
Same here. Every time a new local model comes out, I give it a spin with a pretty vanilla coding task ("refactor this method to take two parameters instead of one", or "fix this class of compiler warning across the ~20 file codebase") and more often than not, they get in endless loops, or fail in very unusual ways. They don't yet even approach the usefulness of SOTA models. It's obviously not a fair comparison, thoug…
You can do this with really small models but you have to do a more legwork. I wouldn't expect most trivially small models to handle anything more than 1 file reliably. The new qwen 3.6 is different though, I have heard cases where it is behaving close to sonnet.
That said I don't see why people are so scared to touch code even if it saves them 500 euro a month. Using my IDEs find across my repo and auto replacing 2 patterns is trivial to do and way faster to do by hand. I mostly use small models, it prevents a lot of the issues I've seen with large models and vibe/agentic coding medium to long term. I also write a lot of code.
Re: Running local LLMs offline on a ten-hour flight
#15To be honest, I think possibility to work and travel is con rather than perk of current times.
Re: Running local LLMs offline on a ten-hour flight
#16This has been exactly my experience too. I've tried multiple harnesses (pi, claude code, codex) with multiple variants of qwen3.6 and gemma4 driven by both o mlx and ollama - and every single time I try to do anything meaningful I end up in a loop. On a 64GB Macbook Pro M3 Max. I really don't know what the hell people are doing locally, and suspect a lot of the hype around running these models locally is bullshit. Su…
I’m frequently surprised how little I can find online about exactly this - different harnesses for local models and how to set them up. The documentation for opencode with local models is (IMO) pretty bad - and even Claude Opus (!) struggled to get it running. And so far I’ve not found a decent alternative to Claude Desktop.
(I’ve recently discovered that you can pipe local models into Claude’s Code and Desktop, so this is on my list to try).
Re: Running local LLMs offline on a ten-hour flight
#17Trying LLM in the air with a 6.200 EUR laptop... Sorry if it's not exactly relatable..
Re: Running local LLMs offline on a ten-hour flight
#18Qwen 4.6 36B? Do they mean Qwen3.6-35B-A3B?
Yes. The author is really sloppy if that wasn’t clear from the article.
Re: Running local LLMs offline on a ten-hour flight
#19tried doing exactly this with ollama on a cross-country flight last month. my macbook basically turned into a jet engine and the battery died in under an hour.
curious if you had to heavily throttle the cpu or stick to super small quants (like 4 bit phi3) to actually make it through 10 hours without a power outlet?
Re: Running local LLMs offline on a ten-hour flight
#20That window seat with the 14” laptop seems extremely claustrophobic. That’s the real limitation on an economy flight - space rather than power or the internet… at least it would be for me. The only times I was able to get my laptop out and do some productive work was when I either was sitting in premium economy isle seat with room to spare or when there was an empty seat next to me
I'd probably choose the window seat myself, because while it is cramped, it is predictably so. When I sit in an aisle seat, it's not as cramped but I regularly get shoulder checked by passing people or beverage carts. What really makes me nervous if I'm in an economy seat is the seat in front of me. Depending on how the seat is designed, if the person suddenly reclines (or hell, just flexes the seat a bunch while mov…
That was the first thing I thought of when I saw the image. That's a very expensive computer that you risk destroying when the 300lb guy in front of you decides to lean back.
The ergonomics of using a laptop on an economy-class tray table are not worth it. You're sitting there like a T-rex trying to make your arms as small as possible to tap on the keys. And the vertical viewing angle to your screen sometimes prevents you from even seeing anything. I wouldn't even bring my laptop out during a flight.