Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

venturebeat.com

Post reply on HN
Print view View original

71–80 of 286 posts

Re: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

#71

Post by CharlesW »

DetroitThrow wrote: post #45
CharlesW wrote: post #35

Earlier quoted context omitted.

Sure, marketing people gonna market. But Haiku's 'extended thinking' mode is very different than the reasoning capabilities of Sonnet or Opus. I would absolutely believe mar-ticles that Qwen has achieved Haiku 4.5 'extended thinking' levels of coding prowess.

>Sure, marketing people gonna market. Oh HN never change.

Not sure what this means, but as a marketing person myself, here's what happened: One day, an Anthropican involved in the Haiku 4.5 launch shrugged, weighed the odds of getting spanked for equating "extended thinking" with "reasoning", and then used Claude to generate copy declaring that. It's not rocket surgery!

Re: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

#72

Post by icase »

MarsIronPI wrote: post #42
xenospn wrote: post #4

Are there any non-Chinese open models that offer comparable performance?

I think you could look into Minstral. There's also GPT-OSS but I'm not sure how well it stacks up. What's your problem with Chinese LLMs?

it’s not obvious to you why someone would want to avoid models created by our enemies?

Re: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

#73

Post by lm28469 »

stavros wrote: post #64
zozbot234 wrote: post #55

Earlier quoted context omitted.

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.

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 Sonne…

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 on local computers

#74

Post by andoando »

stavros wrote: post #64
zozbot234 wrote: post #55

Earlier quoted context omitted.

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.

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 Sonne…

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 on local computers

#75

Post by stavros »

lm28469 wrote: post #73
stavros wrote: post #64

Earlier quoted context omitted.

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 Sonne…

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

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 on local computers

#76

Post by PunchyHamster »

lachiflippi wrote: post #56
PunchyHamster wrote: post #48

I asked it to recite potato 100 times coz I wanted to benchmark speed of CPU vs GPU. It's on 150 line of planning. It recited the requested thing 4 times already and started drafting the 5th response. ...yeah I doubt it

Qwen3.5 pretty much requires a long system prompt, otherwise it goes into a weird planning mode where it reasons for minutes about what to do, and double and triple checks everything it does. Both Gemini's and Claude Opus 4.6's prompts work pretty well, but are so long that whatever you're using to run the model has to support prompt caching. Asking it to "Say the word "potato" 100 times, once per line, numbered.", f…

good to know, thanks. I just ran ollama with qwen3.5:27b. Currently it's stuck on picking format

    Let's write.
    Wait, I'll write the response.
    Wait, I'll check if I should use a table.
    No, text is fine.
    Okay.
    Let's write.
    Wait, I'll write the response.
    Wait, I'll check if I should use a bullet list.
    No, just lines.
    Okay.
    Let's write.
    Wait, I'll write the response.
    Wait, I'll check if I should use a numbered list.
    No, lines are fine.
    Okay.
    Let's write.
    Wait, I'll write the response.
    Wait, I'll check if I should use a code block.
    Yes.
    Okay.
    Let's write.
    Wait, I'll write the response.
    Wait, I'll check if I should use a pre block.
    Code block is better.
... (for next 100 lines)

Re: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

#77

Post by stavros »

andoando wrote: post #74
stavros wrote: post #64

Earlier quoted context omitted.

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 Sonne…

They're great for some product use cases where you dont need frontier models.

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 on local computers

#78

Post by zozbot234 »

lm28469 wrote: post #73
stavros wrote: post #64

Earlier quoted context omitted.

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 Sonne…

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

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 on local computers

#79

Post by vlovich123 »

lm28469 wrote: post #69
mstaoru wrote: post #53

I periodically try to run these models on my MBP M3 Max 128G (which I bought with a mind to run local AI). I have a certain deep research question (in a field that is deeply familiar to me) that I ask when I want to gauge model's knowledge. So far Opus 4.6 and Gemini Pro are very satisfactory, producing great answers fairly fast. Gemini is very fast at 30-50 sec, Opus is very detailed and comes at about 2-3 minutes.…

> Wonder what am I doing wrong? You're comparing 100b parameters open models running on a consumer laptop VS private models with at the very least 1t parameters running on racks of bleeding edge professional gpus Local agentic coding is closer to "shit me the boiler plate for an android app" not "deep research questions", especially on your machine

The hardware difference explains runtime performance differences, not task performance.

Speculation is that the frontier models are all below 200B parameters but a 2x size difference wouldn’t fully explain task performance differences

Re: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

#80

Post by ses1984 »

vlovich123 wrote: post #79
lm28469 wrote: post #69

Earlier quoted context omitted.

> Wonder what am I doing wrong? You're comparing 100b parameters open models running on a consumer laptop VS private models with at the very least 1t parameters running on racks of bleeding edge professional gpus Local agentic coding is closer to "shit me the boiler plate for an android app" not "deep research questions", especially on your machine

The hardware difference explains runtime performance differences, not task performance. Speculation is that the frontier models are all below 200B parameters but a 2x size difference wouldn’t fully explain task performance differences

Who would have thought ai labs with billions upon billions of r&d budget would have better models than a free alternative.
Post reply on HN