Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jacobgold on Monday June 15, 2026 @01:57PM (#48544836)

"Quality is like running edge models from 8-12 months ago."

That sounds great for hobbyists but IMHO it wasn't until Opus 4.6 was released six months go (Dec 25, 2025) that we had a model good enough for professionals to use as a primary driver of their coding agents. That seems to be the threshold worth aiming for.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by sbrother on Monday June 15, 2026 @02:16PM (#48545069)

I strongly agree on that being the release where these tools got good enough to substantially speed up my professional work. I have to admit I was super skeptical of AI coding until then.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by dnautics on Monday June 15, 2026 @02:43PM (#48545363)

for me (might be because of the language im using) i had a substantial bump around september and a huge bump around January.

in my stuff now i use an OT library that claude put finishing touches on in September.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by deaux on Tuesday June 16, 2026 @02:56AM (#48551562)

Your skepticism led you to underrate the usefulness until then. Those who have been using agentic coding for the last 2 years can tell you Opus 4.6 was not a step change in quality, it was mostly a step change in the Overton Window and narrative.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by Projectiboga on Monday June 15, 2026 @02:29PM (#48545213)

So thalen it might be 6-8 months to get to useable on a local open model? Of course state of the art will be a year ahead, a generation at the current pace.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by pierotofy on Monday June 15, 2026 @02:01PM (#48544879)

I use it for work.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jacobgold on Monday June 15, 2026 @02:08PM (#48544967)

That's cool if you prefer it, but it is hard to imagine it being a strictly rational choice when much better quality is available at a price that is small relative to the cost of an employee. Or is there something specific about your use-case?

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by vector_spaces on Monday June 15, 2026 @02:21PM (#48545133)

Not all work requires every facet to be so sharply optimized, and there may be other constraints that are completely invisible to you. Some that were easy for me to imagine: the parent works in a heavily regulated industry, their IT team is slow-moving and paranoid and this is a safe, under-the-radar workaround, the output is "good enough" for their purposes and they find tinkering with it to be fun.

Regardless I don't think it's fruitful to be so condescending with such little insight into this person's situation. Even if you had total insight -- let people be and withhold your judgement, or at least keep it to yourself. Making people feel stupid is a great way to turn people off to pretty much anything else you have to say

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by lokar on Monday June 15, 2026 @02:27PM (#48545195)

Won’t it depend on what you use it for? A less capable system might be fine for boilerplate, moderate re-factoring, etc. Not everyone is building whole features in one go.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by pierotofy on Monday June 15, 2026 @02:47PM (#48545417)

To me, what's not rational is believing you must rent the tools of your trade while exposing all of your employer's intellectual property to a third party. Difference of opinion.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jacobgold on Monday June 15, 2026 @03:05PM (#48545630)

It's not my opinion that you "must" rent tools but it certainly is the pragmatic choice in 2026. I would be as happy as anyone for this situation to change and I expect it to at some point.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by epolanski on Monday June 15, 2026 @07:38PM (#48548618)

Why don't you people bother to try instead of chasing the latest shiny thing?

You must be the type of crowd that writes websites with React and Tailwind and pretend to be engineers and have an opinion on everything.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by storus on Monday June 15, 2026 @07:49PM (#48548704)

You can already get Opus 4.6 level of performance on subtasks with some local models. So you need to pick a proper code writer, plan writer, code tester etc. model that matches your target expectations and use a coding tool that allows calling different LLMs for different subtasks. For example, people use StepFun 3.x or DeepSeek4-Flash for planning, Qwen3.6-27B for coding.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by alexandra_au on Monday June 15, 2026 @11:17PM (#48550135)

You have your dates and models wrong, it was Opus 4.5 released in November 2025, that changed everything, Opus 4.6 was released in February 2026.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jacobgold on Monday June 15, 2026 @11:32PM (#48550231)

You're right. December is when things felt differnt but Opus 4.5 was actually released November 24, 2025.

https://www.anthropic.com/news/claude-opus-4-5

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by kelnos on Tuesday June 16, 2026 @01:37AM (#48551016)

Not sure what you mean by "primary driver", but I was finding even Sonnet quite useful for coding tasks, even about 12-14 months ago (I was too cheap to pay more than $20/month back then, and Opus hit my limits too quickly).

Certainly I get a ton more value out of Opus today, but I could absolutely see someone deciding to limit themselves to 8-to-12-months-ago Opus performance for privacy (or other) reasons.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by trueno on Monday June 15, 2026 @02:04PM (#48544922)

i have a 128gb m4 max macbook pro i've been wanting to tinker with this stuff but genuinely never find the time. any mac users in here running similar to the above that can share their experience?

i always see great debates with local stuff but the space is constantly moving goalposts and all the vernacular is pretty unfamiliar to me. i'd love to understand what people with objective experience feel they've traded away (or gained) when going local so i can determine for myself if these things are a good fit.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by brycesub on Monday June 15, 2026 @02:27PM (#48545198)

If you have a 128GB Mac you really ought to try out: https://github.com/antirez/ds4 by the creator of redis. This is probably as close to it gets to state-of-the-art local LLM + agentic coding.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by lostlogin on Monday June 15, 2026 @03:01PM (#48545582)

Thank you.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by trueno on Monday June 15, 2026 @04:38PM (#48546734)

well this is supremely interesting thanks for putting it on my radar

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by __mharrison__ on Monday June 15, 2026 @05:09PM (#48547053)

Using this just this morning on my DGX Spark. A little slower than frontier models but my $200/mo weekly usage exhausted with 3 days left on the week...

(Shouldn't have done that refactoring job in high mode)

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by htrp on Monday June 15, 2026 @02:17PM (#48545087)

Use your ClaudeCode sub and tell it to set it up for you

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by dirkolbrich on Monday June 15, 2026 @05:18PM (#48547146)

I have the same machine. You might look into https://omlx.ai/ a „macOS-native MLX server“. pi.dev for the agent with MCP, web-search and sub-agents extension.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by atomicnumber3 on Monday June 15, 2026 @01:45PM (#48544684)

Same. I have no desire to use Claude at all anymore.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by pierotofy on Monday June 15, 2026 @01:53PM (#48544796)

Yep. Screw Anthropic, CloseAI and all other rent seekers in this space.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by akulbe on Monday June 15, 2026 @03:04PM (#48545615)

I have an M2 Max MBP with 96GB of RAM. What models and setup would you use for this kind of configuration?

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by monirmamoun on Monday June 15, 2026 @04:25PM (#48546573)

download LM Studio to play with, and it will let you search for models... try Qwen3.6-35B-A3B at 4,5 or 6 bits (6 bit XL is near perfect) and use pi coder or another harness to access it... you can also try Unsloth studio and try same model to start. LM Studio slighter easier to use, Unsloth probably better quality. Neither one is super great quality by the way (meaning: they crash or act weirdly too often to be full production solutions, but can work for local coding). ONCE YOU DOWNLOAD EITHER APP... it will let you search huggingface for the models. Just type qwen to start looking and ... start messing around. And you connect the pi coder harness using the http interface that LM Studio and Unsloth offer to the engine API, so make sure you figure out that url and turn it on... something like 127.0.0.1:1234/api would be a typical IP (localhost) and port (1234 is used by LM Studio)

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by daveidol on Monday June 15, 2026 @02:12PM (#48545023)

Do you do your dev work on the windows machine (referenced in the docs), or do you remotely access it from a separate machine? I ask because I have a RTX 3090 kicking around in a gaming desktop, but I don't use it for any dev work (I use a Macbook Pro).

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by snake_n_my_boot on Monday June 15, 2026 @04:20PM (#48546530)

I have a similar set up and have been using it to learn and tinker with open models. I run Ollama on the gaming desktop and point OpenCode to it from my MacBook. Works nicely for me so far.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by NamlchakKhandro on Tuesday June 16, 2026 @06:56AM (#48553304)

don't waste your time with windows.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by lelandbatey on Monday June 15, 2026 @01:58PM (#48544849)

I use it, it's good, I get work done, but know that they really mean it when they say

> "Quality is like running edge models from 8-12 months ago"

Don't expect Opus, expect more like Haiku. If you micromanage it, you'll get great results. If you want it to be a human in a box, it'll flounder.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by dheera on Monday June 15, 2026 @02:02PM (#48544904)

Am I doing something wrong or has ollama become shittified?

I'm looking at https://ollama.com/search and the top few models like kimi-k2.7-code say "cloud" and I can't seem to ollama pull them.

I thought the whole POINT of ollama was not-cloud?

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by hoherd on Monday June 15, 2026 @02:26PM (#48545179)

I experienced the same situation a month or two ago. One of my friends sent me this article that was illuminating. https://sleepingrobots.com/dreams/stop-using-ollama/

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jubilanti on Monday June 15, 2026 @04:01PM (#48546299)

> I thought the whole POINT of ollama was not-cloud?

It was at first, then the developers realized they had a massive userbase they could monetize. A tale as old as open source...

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by satvikpendem on Monday June 15, 2026 @02:10PM (#48545001)

Ollama is not recommended to be used. Use llama.cpp.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by jmorgan on Monday June 15, 2026 @02:38PM (#48545301)

The larger models are available on Ollama's cloud as most folks don't have the hardware to run 500B-1T parameter models.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by toyg on Monday June 15, 2026 @02:20PM (#48545124)

Yes, you've nailed it. Ollama are desperately trying to pull a Cursor - like 3791 other projects in this space.

[ Parent | on HN ]

Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by dominotw on Monday June 15, 2026 @01:57PM (#48544840)

how much does the setup cost if i want to buy all the hardware now and increased power costs?

[ Parent | on HN ]