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

Kimi K2.7-Code: open-source coding model with better token efficiency

huggingface.co

Post reply on HN
Print view View original

161–170 of 254 posts

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#161

Post by predkambrij »

kmike84 wrote: post #39
shreedx wrote: post #10

I would really love to know if anyone has any experience with something like opencode + Kimi K2.6/2.7 now compared to Claude Code. What is better, what is worse, what is the cost comparison. I am currently paying $100 for the 5x Max plan, but Fable is running through the usage limits quite drastically and I cannot really say it's night and day compared to Opus. Also, I use this mostly for my side projects, so the $10…

I do have this experience. I've used Claude Code (with Opus mostly), and then switched to opencode (mostly with Kimi 2.6) for my personal projects; it's based on a couple months of use. Claude Code is better. But Opencode + kimi 2.6 is workable, which is big. For bare code writing, if you know what exactly you want, most popular models are fine (deepseek, kimi, etc), it feels more or less the same as anthropic models…

To my experience claude/codex $20 are even more subsidized, so running on sonnet or gpt5.4 again gives you more usage.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#162

Post by hootz »

dcreater wrote: post #62
jdw64 wrote: post #43

Personally, when I use open code or routers, I feel that beyond a certain level, the models don't make a huge difference to me. Except for expensive and mediocre models like Gemini. In that sense, Chinese models are pretty good. I usually write code in function or method units and then design and assemble them together. GPT series models are more thorough and better, but I'm not sure if the difference is enormous. It…

I really hope we stop using the term "Chinese models". It has this air of Negative connotation. It's the equivalent of calling cars Japanese, which people used to do but now is almost entirely meaningless. You just call them Toyota, Honda, Lexus etc.

For me, it has a positive connotation! In my experience, Chinese Model means cheaper, but still quite effective model you can use for millions of tokens without burning your entire wallet in seconds. That's why I get more excited over a Chinese model release over American models.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#163

Post by kouteiheika »

SubiculumCode wrote: post #141
kouteiheika wrote: post #131

Earlier quoted context omitted.

Doesn't matter, because they're open-weight, so I can just download them to my PC and... hey, look, now they're owned by me! Unlike the "good" Western counterparts which are all fully proprietary. (Except Mistral, but they're nowhere near SOTA.)

What is hidden in the weights matters.

Ah yes, those pesky Chinese backdoors that no single instance was ever found, even though Chinese open-weight model are a thing for many years now. Many people burn through millions of tokens on these models every day - surely someone would have triggered one of those backdoors, right?

Or that pesky CCP censorship and propaganda baked into the model, which any random guy can remove from whichever model they want as a single weekend side project with an off-the-shelf tool[1]. (Try it. It's fun. I've done it myself.)

[1]: https://github.com/p-e-w/heretic

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#164

Post by SubiculumCode »

kouteiheika wrote: post #163
SubiculumCode wrote: post #141

Earlier quoted context omitted.

What is hidden in the weights matters.

Ah yes, those pesky Chinese backdoors that no single instance was ever found, even though Chinese open-weight model are a thing for many years now. Many people burn through millions of tokens on these models every day - surely someone would have triggered one of those backdoors, right? Or that pesky CCP censorship and propaganda baked into the model, which any random guy can remove from whichever model they want as a…

I agree it is an empirical question. I do not know if that research has been done in the open sphere. But please, do not pretend that there isn't a real geopolitical rivalry going on that makes such questions a legitimate, non-fruity concern.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#165

Post by Symmetry »

I wish they wouldn't call these "open source" models. The output weights are open but that's more analogous to a binary. The source would be the training data and techniques that went into producing the binary/weights.

"Open weights" is also a term in wide use and accurately tells us what we're getting.

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#166

Post by skrtskrt »

giancarlostoro wrote: post #40

Reading their modified license terms, it cracks me up, because they've basically remade the MIT to be the MIT + the one clause that the BSD used to have, which didn't care about MAU or revenue, if you used it in a product, they asked you to 'advertise' them basically. Honestly, its a reasonable request.

It seems tacked on pretty quickly - I would have expected they try a little more legalese regarding what counts as a "user interface".

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#167

Post by WarmWash »

FooBarWidget wrote: post #153
kennywinker wrote: post #88

Earlier quoted context omitted.

Have you looked, or you’re just waiting for someone to hand it to you?

The burden of evidence is on the accuser.

Its akin to the accusation that the UK is a parliamentary system...

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#168

Post by WarmWash »

slopinthebag wrote: post #156
WarmWash wrote: post #132

Earlier quoted context omitted.

The companies are all worker owned, because the state exists for the people, and the state owns everything. At least on paper that's how it is sold. After all it is the Peoples Republic of China.

I mean, if that's the bar then the state owns everything in America as well. After all, you don't really own your land if the state can regulate what you do on it, what it can be used for, what you can build on it, and can take it away if they really need it. The state owns the land, the money supply, and regularly restricts and instructs businesses to take or desist from actions. As such, the state owns everything i…

In the US you can take the state to court and win...

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#169

Post by knollimar »

kouteiheika wrote: post #128
theanonymousone wrote: post #123

In OpenRouter, there is an "int4" tag for Moonshot provider of Kimi K2. 7 Code. Isn't that too low, particularly coming from the very developer of the model? Os that a mistake? How is it in their direct API offer?

The model is natively quantized (i.e. it was trained that way in the first place, so this is not a post-training quantization which degrades performance).

Isn't it not completely quantized? I thought there were some dense parts but most is int4?

Re: Kimi K2.7-Code: open-source coding model with better token efficiency

#170

Post by WarmWash »

wmedrano wrote: post #133
WarmWash wrote: post #125

Earlier quoted context omitted.

Seems like everyday Trump has another order struck down by the courts. Sundar can do whatever he wants, but he has no legal obligation to do any of it.

> Trump cannot instruct Google to put picture of dogs on their homepage. I'm sorry, but that was a horrible example. Corporations have no obligation to donate money to the ballroom yet Google has donated millions.

>Corporations have no obligation to donate money to the ballroom yet Google has donated millions.

Imagine living in a country where they have the obligation.

Post reply on HN