Earlier quoted context omitted.
? I was speaking historically, not now
I don't know why you're surprised; you didn't specify you meant historically.
That was the point of the "e.g."
Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
571–580 of 620 posts
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#572Earlier quoted context omitted.
If you believe the benchmarks, Qwen 3.6 35B-A3B already outperforms Claude 4 Opus. Now, there's a bit of a degree to which some of the open source models do some benchmaxxing, and bigger models with more params may always feel like they have more depth. But anyhow, right now you have something that is arguably comparable to Claude 4 Opus on your laptop. I can't really compare myself because I never used it. It looks…
There is no Claude 4 Opus model... It's a series of model, of which the strongest is Opus 4.8, and Qwen 3.6 35B-A3b gets 51.5% on Swe-bench pro to Opus 4.8's 69.2%
Huh? There is a Claude 4 Opus. It was released about a year ago. It is retired by now, in fact, just retired yesterday: https://platform.claude.com/docs/en/about-claude/model-depre...
But it is still available on Google Vertex according to OpenRouter (though it's possible that info is just out of date, it's currently quoting 3tps which is unusably slow): https://openrouter.ai/anthropic/claude-opus-4
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#573I have! I care about data privacy and LLMs being free. I'm using the Pi coding harness but containerized and sandboxed, to make sure it's running completely offline. On my Mac Studio with 128GB RAM (or MacBook with 36GB RAM) I'm using Qwen3.6 35b, with only 3b active parameters so that it runs really fast. I've done a complete redesign for my website's homepage and blog with Django + Wagtail. The latter is interestin…
Try deepseek V4 flash
there goes the rest of my night
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#574Earlier quoted context omitted.
What kind of coding do you do? Do you keep track of frontier models to vibe check the differences and re-evaluate constantly or are you ok with having a nerfed model forever? (not being judmental, just really wanto to know your framework here)
Some of the work I do, I do for an (EU) organisation that doesn't have clear rules or guidelines on the use of AI yet. Though I have seen colleague-developers blatantly putting source code into external Claude-like models, I stay true to my principles and don't. I know for certain that everything that I run through my local, offline Pi Container Sandbox cannot leave the machine, and thus can't result in a data breach…
It’s just a SaaS service like any other. They all want to use your data, but there are terms to make sure they don’t.
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#575Earlier quoted context omitted.
> unsloth/Qwen3.6-35B-A3B-MTP-GGUF I've actually tried this exact same model locally as well.. albeit on just a single 3090 at 128k context and I got around 40-60tok/s with Q4_K quantization. The thing that bugged me the most was really the quality of the output on moderately complex real-world coding tasks. Having to switch between "prompt/vibe" and "manually implement" is such a big context switch burden, because y…
I'm so out of the loop on this stuff, it's the first time in my IT career I feel really behind on things. I've used Claude Opus to quickly and effectively pound out some 100-200 line scripts that integrate with a vendor's API, and it one-shotted them both almost perfectly. I wonder if for a lot of these local models, the scope of the AI assistance should simply be smaller: You architect the tools and the function def…
100-200 like scripts are tiny especially for something easy to scope like a vendor api. Give opus a much, much larger challenge and see what you get back. You really don’t need to see the code much at all anymore except for some steering now and then.
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#576Earlier quoted context omitted.
Thinking doesn’t change output speed. Anthropic’s models are ~ 40–60 t/s median output speed.
Do you have access to Anthropic model weights to run them locally?
No, and having that is not required to know output speed nor the effect of thinking, so I don’t see the point in such a superfluous, indirect question.
As for the question you’re likely asking: benchmarks that include speed across many models and providers available at various places e.g. https://artificialanalysis.ai/leaderboards/models
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#577Earlier quoted context omitted.
And that would be a much better source for a phone number than Googling. Similarly, the docs that ship with software are a better source for command line switches for that software than a search engine or LLM.
The docs that ship with it are a great source for the LLM who will be running the command and monitoring its output, fixing or adjusting whatever in order to complete my goal. Why on earth would I be calling it by hand?
> Why on earth would I be calling it by hand?
So that it's done correctly instead of wrongly
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#578Earlier quoted context omitted.
> You're gonna be googling the CLI switches for at least 10 minutes So there's this really amazing program called "man"
Which is generally slower than Googling, because it's paged content in a terminal which can search only for literal strings?
This was true a decade ago; unfortunately Google has become more or less useless for most purposes at this point
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#579[flagged]
Re: Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
#580Earlier quoted context omitted.
My strix halo board is feeling more useful and less toylike with the recent performance gains combined from MTP, better quantization, and generalized performance improvements across the stack. For example, I can run Unsloth's Gemma4-31B 4-bit QAT model with around 30tg and 200pp. I don't find that to be too slow at all. Particularly because it's nearly full accuracy and good enough for a lot of different stuff I thro…
you can absolutely use it for some workloads, but as soon as you have some extra complexity for a big repo it'll take forever and the economics are so silly to the point that the electricity bill would be comparable to a subscription. I love having the possibility of running things locally if some random dude decide to pull them plug, and give me solice the fact that i can have 100% private inference, but as the main…
Meh. My server can run these models for neglible power draw (like ~130W fully maxed out). That's with ~30 tok/s which isn't that bad. I do agree that they're still nowhere near as good as the frontier models though. I do lean on those when I need to get something done with better quality or at a faster speed.
I've also been using Deepseek V4 pro/flash for some work stuff and I do find them to be much closer to frontier capability. I may try running flash at home soon for very patient edits. :)