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

111–120 of 443 posts

Re: Qwen3-Coder-Next

#111

Post by segmondy »

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.

The green/yellow/red indicators are based on what you set for your hardware on huggingface.

Re: Qwen3-Coder-Next

#112

Post by Alxc1 »

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 must have missed it, but what did Claude disable access for? Last I checked Cline and Claude Max still worked.

Re: Qwen3-Coder-Next

#113

Post by bri3d »

Nemi wrote: post #94
bri3d wrote: post #83

Earlier quoted context omitted.

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.

> The subscription services have assumptions baked in about the usage patterns; they're oversubscribed and subsidized. Selling dollars for $.50 does that. It sounds like they have a business model issue to me.

This is how every cloud service and every internet provider works. If you want to get really edgy you could also say it's how modern banking works.

Without knowing the numbers it's hard to tell if the business model for these AI providers actually works, and I suspect it probably doesn't at the moment, but selling an oversubscribed product with baked in usage assumptions is a functional business model in a lot of spaces (for varying definitions of functional, I suppose). I'm surprised this is so surprising to people.

Re: Qwen3-Coder-Next

#114

Post by tomashubelbauer »

bri3d wrote: post #80
RationPhantoms wrote: post #62

Earlier quoted context omitted.

There is weaponized malaise employed by these frontier model providers and I feel like that dark-pattern, what you pointed out, and others are employed to rate-limit certain subscriptions.

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…

I am curious to see how this will pan out long-term. Is the quality gap of Opus-4.5 over GPT-5.2 large enough to overcome the fact that OpenAI has merged these two bullet points into one? I think Anthropic might have bet on no other frontier lab daring to disconnect their subscription from their in-house coding agent and OpenAI called their bluff to get some free marketing following Anthropic's crackdown on OpenCode.

Re: Qwen3-Coder-Next

#115

Post by adriand »

solumunus wrote: post #54
markab21 wrote: post #20

Earlier quoted context omitted.

It's getting a lot easier to do this using sub-agents with tools in Claude. I have a fleet of Mastra agents (TypeScript). I use those agents inside my project as CLI tools to do repetitive tasks that gobble tokens such as scanning code, web search, library search, and even SourceGraph traversal. Overall, it's allowed me to maintain more consistent workflows as I'm less dependent on Opus. Now that Mastra has introduce…

Are you just exposing mastra cli commands to Claude Code in md context? I’d love you to elaborate on this if you have time.

Seconded!

Re: Qwen3-Coder-Next

#116

Post by wilkystyle »

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

Interested to hear how this goes!

Re: Qwen3-Coder-Next

#117

Post by jstummbillig »

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’m not paying to support anticompetitive behaviour

You are doing that all the time. You just draw the line, arbitrarily.

Re: Qwen3-Coder-Next

#118

Post by segmondy »

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…

you do realize claude opus/gpt5 are probably like 1000B-2000B models? So trying to have a model that's < 60B offer the same level of performance will be a miracle...

Re: Qwen3-Coder-Next

#119

Post by volkercraig »

simonw wrote: post #109
giancarlostoro wrote: post #63

Earlier quoted context omitted.

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

I buy the theory that Claude Code is engineered to use things like token caching efficiently, and their Claude Max plans were designed with those optimizations in mind. If people start using the Claude Max plans with other agent harnesses that don't use the same kinds of optimizations the economics may no longer have worked out. (But I also buy that they're going for horizontal control of the stack here and banning o…

Absolutely. I installed clawdbot for just long enough to send a single message, and it burned through almost a quarter of my session allowance. That was enough for me. Meanwhile I can use CC comfortably for a few hours and I've only hit my token limit a few times.

I've had a similar experience with opencode, but I find that works better with my local models anyway.

Re: Qwen3-Coder-Next

#120

Post by ad »

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.

which tools?
Post reply on HN