News for hackers. Stuff that matters.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by zozbot234 on Saturday February 28, 2026 @06:01PM (#47201364)
Running local AI models on a laptop is a weird choice. The Mini and especially the Studio form factor will have better cooling, lower prices for comparable specs and a much higher ceiling in performance and memory capacity.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by stavros on Saturday February 28, 2026 @06:09PM (#47201459)
I can never see the point, though. Performance isn't anywhere near Opus, and even that gets confused following instructions or making tool calls in demanding scenarios. Open weights models are just light years behind.

I really, really want open weights models to be great, but I've been disappointed with them. I don't even run them locally, I try them from providers, but they're never as good as even the current Sonnet.

Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by vunderba on Saturday February 28, 2026 @07:16PM (#47202119)
I can't speak to using local models as agentic coding assistants, but I have a headless 128GB RAM machine serving llama.cpp with a number of local models that I use on a daily basis.

- Qwen3-VL picks up new images in a NAS, auto captions and adds the text descriptions as a hidden EXIF layer into the image, which is used for fast search and organization in conjunction with a Qdrant vector database.

- Gemma3:27b is used for personal translation work (mostly English and Chinese).

- Llama3.1 spins up for sentiment analysis on text.

Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by stavros on Saturday February 28, 2026 @07:34PM (#47202273)
Ah yeah, self-contained tasks like these are ideal, true. I'm more using it for coding, or for running a personal assistant, or for doing research, where open weights models aren't as strong yet.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by vunderba on Saturday February 28, 2026 @07:58PM (#47202421)
Understood. Research would make me especially leery; I’d be afraid of losing any potential gains as I'd feel compelled to always go and validate its claims (though I suppose you could mitigate it a little bit with search engine tooling like Kagi's MCP system).
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by andoando on Saturday February 28, 2026 @06:18PM (#47201541)
They're great for some product use cases where you dont need frontier models.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by stavros on Saturday February 28, 2026 @06:21PM (#47201568)
Yeah, for sure, I just don't have many of those. For example, the only use I have for Haiku is for summarizing webpages, or Sonnet for coding something after Opus produces a very detailed plan.

Maybe I should try local models for home automation, Qwen must be great at that.

Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by lm28469 on Saturday February 28, 2026 @06:17PM (#47201534)
They're like 6 months away on most benchmarks, people already claimed coding wad solved 6 months ago, so which is it? The current version is the baseline that solves everything but as soon as the new version is out it becomes utter trash and barely usable
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by zozbot234 on Saturday February 28, 2026 @06:21PM (#47201569)
That's very large models at full quantization though. Stuff that will crawl even on a decent homelab, despite being largely MoE based and even quantization-aware, hence reducing the amount and size of active parameters.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by stavros on Saturday February 28, 2026 @06:20PM (#47201554)
That's just a straw man. Each frontier model version is better than the previous one, and I use it for harder and harder things, so I have very little use for a version that's six months behind. Maybe for simple scripts they're great, but for a personal assistant bot, even Opus 4.6 isn't as good as I'd like.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by wat10000 on Saturday February 28, 2026 @07:04PM (#47201991)
I have a laptop already, so that's what I'm going to use.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by satvikpendem on Saturday February 28, 2026 @06:38PM (#47201745)
I can take a laptop on the train.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by mstaoru on Sunday March 01, 2026 @10:32AM (#47207604)
So it's back to the original question, why spend $5-10k on the Studio, when it will still be 10x slower and half the intelligence vs. $20 Sonnet?.. What is the point (besides privacy) to use local models now for coding?

PS: I can understand that isolated "valuable" problems like sorting photo collection or feeding a cat via ESPHome can be solved with local models.

Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by zozbot234 on Sunday March 01, 2026 @12:43PM (#47208867)
You can't use a $20 Sonnet subscription for general agentic use cases, you have to pay for API use on a per-token basis. The $20 and $200 subscriptions are widely considered unsustainable as such. If anything, the real competition is third-party cheap inference providers.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by NorwegianDude on Sunday March 01, 2026 @05:37PM (#47211452)
At least for me, it's cheap. Even Claude Haiku 4.5 would cost over $60 each day for the same token amount, after accounting for electricity costs. I have the hardware for other reasons anyway, so why not use it, avoid privacy issues and save money.

Are the LLMs very useful? That is a whole other discussion...