Hacker News new | past | comments | ask | show | jobs | submit
They've also announced Qwen3.8-27B being released open-weight next week. Qwen3.6-27B is widely regarded as one of the best local models, especially since nothing else comes close to it, that isn't benchmaxxed, without being significantly larger. If 3.8 truly improves upon it that would be awesome.
Qwen3.6-35B is my daily driver for AI, and what convinced me to cancel my Claude subscription back in April. The Qwen3.6 line is easily the best local model I've tried, and I've tried a lot. I've got it diligently grinding away on my laptop right now, reviewing and fixing some bugs in my F# code.
Qwen-3.6-35B-A3B was our "gateway drug" into switching our organisation to agent/harness-first coding.

Particularly, I had one team member who was extremely sceptical of AIs/LLMs/harnesses and refused to use them. One day he said "Well, I have an RTX 5090 doing nothing... should I try to get something up on it?" and a few minutes later he had 3.6-35B loaded up, running OpenCode.

It continues to be a workhorse to this day, running on both my local Mac for various types of jobs, an AMD R9700 at the office, and said teammember still uses it on his 5090, although in practical terms we do a lot more with DS-V4-Flash-0731 these days.

I’ve run 3.6-27B and 3.6-35B on 32GB locally for a lot of bulk non-code tasks. Let it run overnight and wake up to millions of output tokens worth of results without data having left my house, all for the price of electricity.

I haven’t found it very useful for code. It can do some code, but I’ve tried a dozen different quants and context lengths and the output is always bad enough that it has to be discarded for anything other than really easy tasks. It has been useful for exploring codebases for search and summary, though.

DS Flash is where local models begin to feel useful for coding, but the quants we run locally are sharply reduced in intelligence from the benchmarks for the full models.

For applications where data cannot leave the local network it’s good to have them. For actual coding work I can’t actually justify the power of electricity and cooling, let alone the expensive hardware, compared to hosted APIs.

But I admit I do enjoy playing with them anyway. I think it’s one of those hobbies where it’s most fun if you never do the math on how much you’re paying for the privilege. If someone has a requirement that data stay local then it’s different, of course.

loading story #49156109
loading story #49158404
loading story #49158976
What!? You are skeptical of AI but will go through the manual process of hosting a model that’s less than frontier intelligence (talking about Qwen 3.6)? Anti-AI folks are always odd to me
A local model needs 0 investment and 0 commitment, takes literal minutes to get started (especially if you have someone who is into that stuff showing you the ropes) and if you end up disliking the experience of using AI you can just `rm -fr` it and forget the whole thing existed.
Needs 0 investment and 0 committment?

- You at least need a capable machine, so that's not 0 monetary investment. - You need to spend at least an hour decicding between ollama, llamacp, mlx, etc. - You need to find the correct quantized version of the model that works for you based on the architecture. - You need to figure out the correct context window size to get reasonable performance. - You need to setup a harness that works against your model - You might need to setup additional websearch tools, image tools, etc since harnesses like pi don't come with the model. Ofc you can't use codex and claude code, because those aren't opensource and you are anti-AI.

Or, you could sign up for Opencode for $10 and just be productive.

I'm particularly calling out the hypocrisy of the original comment. Being Anti-AI, and then spending hours on setting up a less than frontier AI model.

loading story #49154852
You might be anti-ai in the sense you aren’t comfortable with all your data being shipped back and forth to a third party.
loading story #49155848
loading story #49155337
loading story #49153468
loading story #49156946
loading story #49153475
loading story #49153629
loading story #49153572
loading story #49155386
Local models on regular hardware aren't really capable of anything. Whatever you're testing is nowhere near a measly $20/mo subscription, so it's of limited use.
loading story #49156685
This is the diametric opposite of the rent-vs-buy scenario that this entails.

Local: You need to invest $thousands into GPU and/or very-high-end CPU+Memory hardware.

Vendor: You can use any existing device, even a phone or tablet. A very low-end laptop is fine.

> takes literal minutes to get started

Local: Typical scenario is hours just to download the software, the model weights, and then faffing around with CUDA and matching your GPU drivers.

Vendor: Free-tier available instantly on a web URL. Even local agents have free tiers from multiple vendors. Install is a single command and/or download and "next,next,next,finish" wizard that takes ~1 minute.

> you can just `rm -fr` it and forget the whole thing existed.

I'm still cleaning up multi-GB model weights floating around in hidden subdirectories under my user profile from months ago when I was experimenting with local models!

Meanwhile I simply... stopped using Gemini. That was the entire process: I no longer actively use it. They stopped billing me for my token usage, because it is now zero. That's... it.

You have it totally backwards.

> I'm still cleaning up multi-GB model weights floating around in hidden subdirectories under my user profile from months ago when I was experimenting with local models!

Are you trying to say that local models are hard to use because... you're having issues handling files properly? I am not sure I get the argument.

I get the rest of the comment: local models require an investment upfront, and it is less convenient. It doesn't say that it is not cheaper, though.

loading story #49153884
It took me about three hours total to set up a local model. I already have a GPU and I have fiber for the download. llama.cpp is not difficult to compile and has many backends. It can run parts of the model on different backends, like in the common case that the GPU doesn't have enough VRAM for everything. There are many step-by-step guides available.
loading story #49156985
> "I'm still cleaning up multi-GB model weights floating around in hidden subdirectories under my user profile from months ago when I was experimenting with local models!"

I used to deal with these kinds of frustrations too.

    fd --unrestricted --size +1G

    fd --help

    -u, --unrestricted...
        Perform an unrestricted search, including ignored and hidden files. This is an alias for
       '--no-ignore --hidden'.

    -S, --size size
        Limit  results  based  on  the  size  of  files  using  the  format
        <+-><NUM><UNIT>
Huh what? Qwen3.5-35B-A3B runs just fine with maximum context, on an RTX SUPER 12 GB, with offloading of some expert layers to DDR4-3200.

Same story on an RTX 4060 Ti 16 GB. MTP is a serious boost to tg.

Downloading the model is a simple hf command that HuggingFace's web UI even gives you.

llama.cpp is trivial to use, and so is llama-swap, if you want to use other models too.

If you don't know what arguments to run it with, you download ggrun and use that.

Local LLMs are incredibly capable and don't need expensive hardware. A $500 GPU will do. Or even cheaper.

This is all trivial.

loading story #49154434
loading story #49154076
loading story #49156837
This largely describes me. I'm skeptical of AI in that it's capabilities, while very impressive, are vastly oversold and overblown. Being skeptical of AI is not being "Anti-AI". That's largely the AI data centers are using up all the water and electricity types.
Maybe you're anti-AI because you're really anti-outsourcing your thinking to some remote corporation you don't control?

That's one of my main issues with AI anyways, the thought of having all my data go through some sketchy foreign (to me) entity with questionable motives and under a questionable regime.

Local AI solves for all of those.

I'm not against AI. I'm calling out the hypocrisy in the comment. I'm anti-AI, but will spend hours trying to setup a local model, instead of just getting access to frontier intelligence in 15 mins, and actually getting useful work done.

If you're learning about model inference, then it's a different and you are definitely not anti-AI in that case.

loading story #49153772
35B MoE is certainly a good and fast local model. I find 27B dense to be quite a bit smarter, so I daily drive that. I wish there was a ~100B MoE with maybe 10B active. It would be super smart and fast!
loading story #49151023
loading story #49152194
loading story #49152759
loading story #49152354
loading story #49151120
It was for me too but the new deepseek pricing is too good to ignore for now.

I honestly think that with my electricity prices running qwen 36B myself is more expensive than hitting the cache rate at deepseek.

loading story #49152920
I would recommend looking into Ornith1.0 - it's using Qwen3.6 35B-A3B and excels in coding, at least for my coding needs, Python, web-dev, SQL scripting and some C#. Using Pi harness.
I have been using Qwen3.6-35B-A3B as my daily driver as well and its been phenomenal when it comes to coding
loading story #49151772
loading story #49156465
With laptop being ...?
Is your Qwen3.6 locally run on your laptop? What kind of tokens/s are you getting from your laptop GPU?
loading story #49154489
compared to claude - how 'fast' is it in terms of throughput on your laptop?
loading story #49151178
loading story #49151061
loading story #49151758
loading story #49151100
loading story #49151170
loading story #49152099
loading story #49156911
I'm a big ole noob when it comes to local AI. What are you using for a harness? Or platform to interact with it?
loading story #49155961
loading story #49153622
On what hardware do you run the model locally, if so?
loading story #49153378
What are the specs of your laptop and what tokens per second do you get?
loading story #49158546
I'm on the verge over here, the new Anthropic models have been a disappointment. I've tried the A3B variant, but had mixed results. What do you use as the coding agent, and have you heavily customized your workflows?
{"deleted":true,"id":49151073,"parent":49150929,"time":1785729613,"type":"comment"}
What laptop?
loading story #49151070
{"deleted":true,"id":49151341,"parent":49150929,"time":1785732697,"type":"comment"}
Qwen3.8-Max is the first in Qwen-Max series to be open-weight as well.

Kimi K3, GLM 5.2 and now Qwen3.8-Max - open weight models.

DeepSeek V4 Flash outperforming Gemini 3.1 pro, probably DeepSeek V4 Pro update is also coming soon

Chinese labs are cooking very hard. US closed weight labs are probably hard time to resist not calling Washington DC for more AI regulations

loading story #49152681
loading story #49158001
Some advice I got from another HN Mac user was to run local models in energy saver mode. You'll get slightly reduced tokens, but the laptop won't overheat and the fans won't go wild.
loading story #49153305
Oh. I've been using an icepack under my laptop to keep mine cool. I'm watching it with llamatop to see if the GPU is actually active or not, aw activity monitor wasn't showing me what I wanted.
loading story #49152602
This is what I've been waiting for. We are still using fine-tuned deployments of Qwen3.6-27B with a lot of success but could use a bump in intelligence. Here's hoping.
loading story #49152058
Really awesome. Though I wish they'd do a dense 48B, 60B or 72B.

There seems to be quite a gap between the small ones and the enormous ones these days.

Qwen 3.6 27b has been the sweet spot for me in terms of local models. I've had good luck using it with Pi harness. Looking forward to this.
loading story #49153588
Having invested in a machine with 128GB of RAM, I would love seeing something a bit larger than 27B / 35B, possibly a 54B dense model or 70B MoE would be much closer to the Qwen 3.8 Max experience.
loading story #49152538
The 27B have many more active parameters than much bigger models such as DS4Flash, MiniMax etc, which makes it punch above its tiny weight. A great fit for a 5090 in a closet for meat-and-potatoes, kind of work.
loading story #49156714
loading story #49157102
loading story #49156561
loading story #49155730
For those of us who don't have the time to follow closely, Qwen3.6-27B being Open Source and Open Weight, what level is this compared to other Western paid version?

Just so that we know what 3.8 would be like.

I currently have about 150 Tabs of Antirez posting on AI and running local model I haven't had the time to read. And there are probably some prerequisite reading or other research in between as well. I just wish there are some very high level overview and news coverage on all these.

loading story #49152408
If they trained it well, and can do computer use, it will be a new era. Companies can keep PCs, put Qwen 3.8 27b on it and get rid of the employees, lol...
loading story #49151686
loading story #49151551
loading story #49155959
loading story #49154788
as much as im excited for it, sadly it gonna be one of the reasons to push ram prices higher