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

Qwen3-Coder-Next

qwen.ai

Post reply on HN
Print view View original

151–160 of 443 posts

Re: Qwen3-Coder-Next

#151

Post by gitpusher »

disiplus wrote: post #96
cedws wrote: post #41

I kind of lost interest in local models. Then Anthropic started saying I’m not allowed to use my Claude Code subscription with my preferred tools and it reminded me why we need to support open tools and models. I’ve cancelled my CC subscription, I’m not paying to support anticompetitive behaviour.

im downloading it as we speek to try to run it on a 32gb 5090 + 128gb ddr5 i will compare it to glm 4.7-flash that was my local model of choice

Likewise curious to hear how it goes! 80B seems too big for a 5090, I'd be surprised if it runs well un-quantized.

Re: Qwen3-Coder-Next

#152

Post by dcastm »

simonw wrote: post #3

This GGUF is 48.4GB - https://huggingface.co/Qwen/Qwen3-Coder-Next-GGUF/tree/main/... - which should be usable on higher end laptops. I still haven't experienced a local model that fits on my 64GB MacBook Pro and can run a coding agent like Codex CLI or Claude code well enough to be useful. Maybe this will be the one? This Unsloth guide from a sibling comment suggests it might be: https://unsloth.ai/docs/models/qwen3…

I have the same experience with local models. I really want to use them, but right now, they're not on par with propietary models on capabilities nor speed (at least if you're using a Mac).

Re: Qwen3-Coder-Next

#153

Post by Tossrock »

tomashubelbauer wrote: post #55
cedws wrote: post #41

I kind of lost interest in local models. Then Anthropic started saying I’m not allowed to use my Claude Code subscription with my preferred tools and it reminded me why we need to support open tools and models. I’ve cancelled my CC subscription, I’m not paying to support anticompetitive behaviour.

Anthropic banned my account when I whipped up a solution to control Claude Code running on my Mac from my phone when I'm out and about. No commercial angle, just a tool I made for myself since they wouldn't ship this feature (and still haven't). I wasn't their biggest fanboy to begin with, but it gave me the kick in the butt needed to go and explore alternatives until local models get good enough that I don't need to…

They did ship that feature, it's called "&" / teleport from web. They also have an iOS app.

Re: Qwen3-Coder-Next

#154

Post by tclancy »

jstummbillig wrote: post #145
tclancy wrote: post #122

Earlier quoted context omitted.

The enemy of done is perfect, etc. what is the point of comments like this?

What is the point of any of this? To exchange how we think about things. I think virtue signaling is boring and uncandid.

Unclench and stop seeing everything as virtual signaling. What about al those White Knight, SJWs in the 70s who were against leaded gas? Still virtue signaling?

Re: Qwen3-Coder-Next

#155

Post by thedangler »

cedws wrote: post #41

I kind of lost interest in local models. Then Anthropic started saying I’m not allowed to use my Claude Code subscription with my preferred tools and it reminded me why we need to support open tools and models. I’ve cancelled my CC subscription, I’m not paying to support anticompetitive behaviour.

How are you using the huge models locally?

Re: Qwen3-Coder-Next

#156

Post by pyvpx »

Propelloni wrote: post #123
bri3d wrote: post #80

Earlier quoted context omitted.

They have two products: * Subscription plans, which are (probably) subsidized and definitely oversubscribed (ie, 100% of subscribers could not use 100% of their tokens 100% of the time). * Wholesale tokens, which are (probably) profitable. If you try to use one product as the other product, it breaks their assumptions and business model. I don't really see how this is weaponized malaise; capacity planning and some fo…

So, if I rent out my bike to you for an hour a day for really cheap money and I do so a 50 more times to 50 others, so that my bike is oversubscribed and you and others don't get your hours, that's OK because it is just capacity planning on my side and widely accepted? Good to know.

I have some bad news for you about your home internet connection.

Re: Qwen3-Coder-Next

#157

Post by zamadatix »

yorwba wrote: post #40
zamadatix wrote: post #10

Can anyone help me understand the "Number of Agent Turns" vs "SWE-Bench Pro (%)" figure? I.e. what does the spread of Qwen3-Coder-Next from ~50 to ~280 agent turns represent for a fixed score of 44.3%: that sometimes it takes that spread of agent turns to achieve said fixed score for the given model?

SWE-Bench Pro consists of 1865 tasks. https://arxiv.org/abs/2509.16941 Qwen3-Coder-Next solved 44.3% (826 or 827) of these tasks. To solve a single task, it took between ≈50 and ≈280 agent turns, ≈150 on average. In other words, a single pass through the dataset took ≈280000 agent turns. Kimi-K2.5 solved ≈84 fewer tasks, but also only took about a third as many agent turns.

Ah, a spread of the individual tests makes plenty of sense! Many thanks (same goes to the other comments).

Re: Qwen3-Coder-Next

#158

Post by tomashubelbauer »

Tossrock wrote: post #153
tomashubelbauer wrote: post #55

Earlier quoted context omitted.

Anthropic banned my account when I whipped up a solution to control Claude Code running on my Mac from my phone when I'm out and about. No commercial angle, just a tool I made for myself since they wouldn't ship this feature (and still haven't). I wasn't their biggest fanboy to begin with, but it gave me the kick in the butt needed to go and explore alternatives until local models get good enough that I don't need to…

They did ship that feature, it's called "&" / teleport from web. They also have an iOS app.

That's non-local. I am not interested in coding assistants that work on cloud based work-spaces. That's what motivated me to developed this feature for myself.

Re: Qwen3-Coder-Next

#159

Post by gitpusher »

Pretty cool that they are advertising OpenClaw compatibility. I've tried a few locally-hosted models with OpenClaw and did not get good results – (that tool is a context-monster... the models would get completely overwhelmed them with erroneous / old instructions.)

Granted these 80B models are probably optimized for H100/H200 which I do not have. Here's to hoping that OpenClaw compat. survives quantization

Re: Qwen3-Coder-Next

#160

Post by fc417fc802 »

tomashubelbauer wrote: post #90
redblacktree wrote: post #84

Earlier quoted context omitted.

How did this work? The ban, I mean. Did you just wake up to find out an email and that your creds no longer worked? Were you doing things to sub-process out to the Claude Code CLI or something else?

I left a sibling comment detailing the technical side of things. I used the `Bun.spawn` API with the `terminal` key to give CC a PTY and mirrored it to my phone with xterm.js. I used SSE to stream CC data to xterm.js and a regular request to send commands out from my phone. In my mind, this is no different than using CC via SSH from my phone - I was still bound by the same limits and wasn't trying to bypass them, Ant…

> Anthropic is entitled to their different opinion of course.

I'm not so sure. It doesn't sound like you were circumventing any technical measures meant to enforce the ToS which I think places them in the wrong.

Unless I'm missing some obvious context (I don't use Mac and am unfamiliar with the Bun.spawn API) I don't understand how hooking a TUI up to a PTY and piping text around is remotely suspicious or even unusual. Would they ban you for using a custom terminal emulator? What about a custom fork of tmux? The entire thing sounds absurd to me. (I mean the entire OpenCode thing also seems absurd and wrong to me but at least that one is unambiguously against the ToS.)

Post reply on HN