Live data from Hacker News

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

news.ycombinator.com

371–380 of 620 posts

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

#371
post #200

Earlier quoted context omitted.

Which Opus? They certainly outperform Claude 3 Opus. Anyhow, feel free to try them out head to head on OpenRouter. I'd love to see someone write up their results, of a modern local sized open source model vs. frontier models from ~a year ago, on something other than the standard benchmarks.

I’m normally comparing frontier open/cheap models against frontier closed source. I use deepseek/glm regularly, they’re fine and you can get real work done with them but it’s super obvious when you switch back to opus or even sonnet. A 3B active param MoE model is not comparable.

Agreed, but at their current prices Deepseek + GLM are clear winners in my book. This weekend I spent $5 between the two where as I'd probably have to pay $20-30 to Anthropic (and that's still with the massive VC subsidies).

For web development (or anything else with an extreme amount of training data) it's number one for sure. You can't beat it at its costs. US companies will not be able to compete on a competitive market, which is why they rely on so much US government protection + corporate welfare.

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

#372
Yes, for client projects where privacy and security is important, but no enterprise contract:

Open code against Infomaniak hosted OSS models: Qwen3.5-122B-A10B-FP8, Kimi-K2.6.

I use API keys for billing. It performs like Dec 2025 in terms of my productivity back then.

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

#373

Yes. Llama.cpp + Qwen3.6-35b (MTP) + OpenCode is quite capable and runs on a single RTX 3090 and is faster than most cloud models. Quality is like running edge models from 8-12 months ago. Setup details at https://github.com/pierotofy/LocalCodingLLM/

"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.

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.

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

#375

Earlier quoted context omitted.

If you're willing to go the AMD route, the AMD Radeon Pro R9700 definitely looks interesting for the price compared to NVidia.

Can we also run LLMs on Radeon?

I run qwen 27B:Q4 @ 130k context at 50 t/s on a single R9700, and have a 7900XT that runs mellum 12B:Q8 as its subagent. R9700s do really well at low wattage and underclocking as well. It's designed to run at 300W, mine is throttled at 210W, and only had an 8% slowdown. If I had somewhere else to put my desktop in my house, I'd bump it up to 240W and there would be zero perf degradation.

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

#376

Earlier quoted context omitted.

"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.

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.

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

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

#377
post #28
post #11

Pretty good results with qwen 3.6 27b dense. I’d say it’s about equal to (Claude) haiku 4.5 maybe sonnet depending on the task.

What tool do you use to drive things for you, out of curiosity?

I use Claude code. You can use it with any model you want to.

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

#378

Earlier quoted context omitted.

> is like a junior with knowledge across the board, that you really need to guide, versus a senior that thinks with you on architecture I don't want to be rude, but your linkedin has a sumtotal (generous) of like 8 months of programming as a profession (job title is AI Engineer). The rest is at best programming adjacent. How would you know what either of these situations are really like?

I haven't logged in to LinkedIn or looked at it since a former employer demanded that everyone create a profile. So mine is now about 20 years out of date.

His is very up to date. Not everyone is you.

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

#380
post #13
post #11

Pretty good results with qwen 3.6 27b dense. I’d say it’s about equal to (Claude) haiku 4.5 maybe sonnet depending on the task.

I’d rather ask my butcher than Haiku for coding tasks

I’d say when qwen works it works like sonnet, when it fails it fails like haiku. So it’s less consistent but works pretty well, I guess? It’s still overall pretty useful for a lot of stuff, and I can run it directly on my MacBook. Once you get an idea of what it can and can’t bite off, it’s pretty easy to break things into chunks it will handle reliably with grace. But I still like to have access to SOTA models for review. Also you can have a SOTA model write a development plan that is basically a bunch of prompts to generate each part, then have the local model follow the plan.

I should mention not to run it at less than q6, I prefer q8.

Post reply on HN