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

81–90 of 443 posts

Re: Qwen3-Coder-Next

#81

Post by CamperBob2 »

giancarlostoro wrote: post #63
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.

I do wonder if they locked things down due to people abusing their CC token.

How do I "abuse" a token? I pass it to their API, the request executes, a response is returned, I get billed for it. That should be the end of the conversation.

(Edit due to rate-limiting: I see, thanks -- I wasn't aware there was more than one token type.)

Re: Qwen3-Coder-Next

#83

Post by bri3d »

cedws wrote: post #78
giancarlostoro wrote: post #63

Earlier quoted context omitted.

I do wonder if they locked things down due to people abusing their CC token.

In what way would it be abused? The usage limits apply all the same, they aren't client side, and hitting that limit is within the terms of the agreement with Anthropic.

The subscription services have assumptions baked in about the usage patterns; they're oversubscribed and subsidized. If 100% of subscriber customers use 100% of their tokens 100% of the time, their business model breaks. That's what wholesale / API tokens are for.

> hitting that limit is within the terms of the agreement with Anthropic

It's not, because the agreement says you can only use CC.

Re: Qwen3-Coder-Next

#84

Post by redblacktree »

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…

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?

Re: Qwen3-Coder-Next

#85

Post by danielhanchen »

CamperBob2 wrote: post #60
danielhanchen wrote: post #14

Earlier quoted context omitted.

UD stands for "Unsloth-Dynamic" which upcasts important layers to higher bits. Non UD is just standard llama.cpp quants. Both still use our calibration dataset.

Please consider authoring a single, straightforward introductory-level page somewhere that explains what all the filename components mean, and who should use which variants. The green/yellow/red indicators for different levels of hardware support are really helpful, but far from enough IMO.

Oh good idea! In general UD-Q4_K_XL (Unsloth Dynamic 4bits Extra Large) is what I generally recommend for most hardware - MXFP4_MOE is also ok

Re: Qwen3-Coder-Next

#86

Post by bri3d »

CamperBob2 wrote: post #81
giancarlostoro wrote: post #63

Earlier quoted context omitted.

I do wonder if they locked things down due to people abusing their CC token.

How do I "abuse" a token? I pass it to their API, the request executes, a response is returned, I get billed for it. That should be the end of the conversation. (Edit due to rate-limiting: I see, thanks -- I wasn't aware there was more than one token type.)

You can buy this product, right here: https://platform.claude.com/docs/en/about-claude/pricing

That's not the product you buy when you a Claude Code token, though.

Re: Qwen3-Coder-Next

#87

Post by danielhanchen »

binsquare wrote: post #22
danielhanchen wrote: post #2

For those interested, made some Dynamic Unsloth GGUFs for local deployment at https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF and made a guide on using Claude Code / Codex locally: https://unsloth.ai/docs/models/qwen3-coder-next

How did you do it so fast? Great work as always btw!

Thanks! :) We're early access partners with them!

Re: Qwen3-Coder-Next

#88

Post by pixelpoet »

gigatexal wrote: post #29
embedding-shape wrote: post #17

Earlier quoted context omitted.

> 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 I've had mild success with GPT-OSS-120b (MXFP4, ends up taking ~66GB of VRAM for me with llama.cpp) and Codex. I'm wondering if maybe one could crowdsource chat logs for GPT-OSS-120b running with Codex, then seed another post-training run to fine-tune the 20b v…

I’ve a 128GB m3 max MacBook Pro. Running the gpt oss model on it via lmstudio once the context gets large enough the fans spin to 100 and it’s unbearable.

Laptops are fundamentally a poor form factor for high performance computing.

Re: Qwen3-Coder-Next

#89

Post by organsnyder »

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…

They run fairly well for me on my 128GB Framework Desktop.

Re: Qwen3-Coder-Next

#90

Post by tomashubelbauer »

redblacktree wrote: post #84
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…

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, Anthropic is entitled to their different opinion of course.

And yeah, I got three (for some reason) emails titled "Your account has been suspended" whose content said "An internal investigation of suspicious signals associated with your account indicates a violation of our Usage Policy. As a result, we have revoked your access to Claude.". There is a link to a Google Form which I filled out, but I don't expect to hear back.

I did nothing even remotely suspicious with my Anthropic subscription so I am reasonably sure this mirroring is what got me banned.

Edit: BTW I have since iterated on doing the same mirroring using OpenCode with Codex, then Codex with Codex and now Pi with GPT-5.2 (non-Codex) and OpenAI hasn't banned me yet and I don't think they will as they decided to explicitly support using your subscription with third party coding agents following Anthropic's crackdown on OpenCode.

Post reply on HN