Qwen3.8-Max: A New Bar for Coding and Cowork
qwen.ai871 points by ai2027 13 hours ago
871 points by ai2027 13 hours ago
As someone who is searching for a new programming contract right now, reading all of the incredible abilities here is pretty intimidating. Especially since I get almost all of my projects from Upwork which is an outsourcing site.
I believe I am competing directly with these frontier models in some circumstances. Like there are a ton of programmers who previously would be outsourcing work to that site, but now they assign that same work to AI agents.
Ever since November 2022 when ChatGPT blew up, I have been focusing on agents in order to try to get ahead of the curve. But I haven't managed to get an agent business off the ground and have been doing poorly paid agentic projects from that site instead.
But now everyone is building agents, and this crazy list of accomplishments makes it look like we are close to the point where the agents are building agents.
In fact the next time I get an Upwork contract for another agent, I actually should run it through my agent and see how far it can get. What I'm seeing a lot of now is requests to automate as much of a business as possible.
Anyway the point is these models are just about capable of doing the entire job of analyzing a small business and building out all the agents and iterating on them with the business owner.
That's actually what I should build is a SaaS that does that. Which I would if I wasn't basically desperate to get another contract this week.
And I know Upwork is bad but I have not had much success with other options on short notice.
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.
> I’ve run 3.6-27B and 3.6-35B on 32GB locally for a lot of bulk non-code tasks.
Do you mind sharing your use cases?
Not OP, but I use it for a ton of smaller things. I have it hooked into Hermes and have been using it to help bulk rename my media folders so they all follow a common format, add titles that sort of thing which wouldn't be easy to 'script'. Another thing I use it for is comparing data sets, looking at my exported Spotify artists and compare to what I have locally, and letting me know where there are missing artists, or albums, and recommendations based on similar artists that I may not have locally.
Sure a lot of this could be done without AI, but it's certainly quicker and easier, and since my AI box is on solar, it's just the power of the sun to keep it going.
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.
Maybe not '0 investment and 0 commitment', but incredibly little depending on what you have laying around. It takes less than 5 minutes to download say LM Studio and an Open Model and as long as you have the hardware to support it, you start moving along. If you are on AMD in some ways it's even 'easier', you can download Lemonade and it will tell you exactly what will fit and best options based on what you are trying to do.
For me at least the local AI stuff, powered with solar has been pretty great. Would that scale to a large business? Goodness no, but for my tinkering and learning, it works great.
> Or, you could sign up for Opencode for $10 and just be productive.
You forgot the step before where you spend months waiting for security to vet it, legal to sign off and procurement to approve it.
Or you could use hardware your team has lying around. Everyone isn’t working on cloud-hosted CRUD APIs.
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.
Im anti AI in the sense of VC backed global warming far right accelerationists.
Local AI is almost perfect. But its like all democracy: its history is marred with lots of crap.
install LM Studio, download the automatically selected quant based on your hardware, start a conversation with the automatic context size. 10 minutes at best and zero effort
All of your objections have already been addressed by the previous comments.
The original comment states that the person in question already had a suitable graphics card to hand, so it did not require a monetary investment.
GP clearly states that "someone who is into that that stuff" was guiding the process, so it did not require a significant time investment.
> 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.
I see no hypocrisy in the original comment.
You've also assumed the skeptic in question doubts the capabilities of AI. That may be the case (like you, I have no idea), but they may also have privacy concerns, in which case a local model is the appropriate choice.
There are plenty of reasons to be skeptical of AI.
> You at least need a capable machine, so that's not 0 monetary investment
It is 0 monetary investment if I already have said machine lying around doing nothing.
Which is exactly the story OP talked about.
But most people don't have an RTX 5090 lying around, so the story doesn't apply to them, right?
You don't need a 5090 to run local AI. A whole lot of people out there are doing it with Macs. Unified ram is the biggest thing.
> 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
Pi has a nice guide on it (https://pi.dev/docs/latest/llama-cpp) and it is really not that hard.
How is that hypocrisy? Self hosting is somehow anti AI? Its not anti AI. Its literally using AI!
…and honestly, at a higher technical level than slapping your wallet against a token provider and running prompts in a hosted sandbox you can't even see the prompts in.
Look man I am incredibly skeptical of how LLM’s have been rolled out and all the promises people make (it’s so much snake oil and pipedreams), but I also found it very trivial to hop on LM studio and start tinkering with models. If you’ve already got a decent midtier computer on hand, which I imagine a lot of us already do, then it’s really not hard to get started and get immediate results.
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.
i really like the idea of running local models but i'm always in the position of wanting the best model(s) available and i don't have any severe privacy concerns. as such i have yet to justify ever using local models.
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.
> you're having issues handling files properly?
I guess they were using ollama, which does not tell you where it puts the models it downloads.
Filelight / ncdu are my friends for finding random 30GB directories containing cached models.