Kimi K2.6: Advancing open-source coding • Hacker News Board

Re: Kimi K2.6: Advancing open-source coding

#61

Post by konart » Mon, Apr 20, 2026, 4:58 PM UTC

osti wrote: post #36

game_the0ry wrote: post #27

There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.

Maybe open source == communism

But China is not communist event though the rulling party the word in its name.

Re: Kimi K2.6: Advancing open-source coding

#62

Post by m4rkuskk » Mon, Apr 20, 2026, 4:58 PM UTC

I have been testing it in my app all morning, and the results line up with 4.6 Sonnet. This is just a "vibe" feeling with no real testing. I'm glad we have some real competition to the "frontier" models.

Re: Kimi K2.6: Advancing open-source coding

#63

Post by zozbot234 » Mon, Apr 20, 2026, 5:00 PM UTC

osti wrote: post #39

NitpickLawyer wrote: post #5

Earlier quoted context omitted.

While I'm skeptical of any "beats opus" claims (many were said, none turned out to be true), I still think it's insane that we can now run close-to-SotA models locally on ~100k worth of hardware, for a small team, and be 100% sure that the data stays local. Should be a no-brainer for teams that work in areas where privacy matters.

I think this one is only about 600GB VRAM usage, so it could fit on two mac studios with 512GB vram each. That would have costed (albeit no longer available) something like less than 20k.

You could run it with SSD offload, earlier experiments with Kimi 2.5 on M5 hardware had it running at 2 tok/s. K2.6 has a similar amount of total and active parameters.

Re: Kimi K2.6: Advancing open-source coding

#64

Post by SwellJoe » Mon, Apr 20, 2026, 5:02 PM UTC

simonw wrote: post #53

Accessed via OpenRouter, this one decided to wrap the SVG pelican in HTML with controls for the animation speed: https://gisthost.github.io/?ecaad98efe0f747e27bc0e0ebc669e94... Transcript and HTML here: https://gist.github.com/simonw/ecaad98efe0f747e27bc0e0ebc669...

We got an overachiever, here. Kimi sounds like a teacher's pet kind of name.

Re: Kimi K2.6: Advancing open-source coding

#65

Post by twotwotwo » Mon, Apr 20, 2026, 5:02 PM UTC

elfbargpt wrote: post #26

I've always been surprised Kimi doesn't get more attention than it does. It's always stood out to me in terms of creativity, quality... has been my favorite model for awhile (but I'm far from an authority)

Kagi has it as an option in its Assistant thing, where there is naturally a lot of searching and summarizing results. I've liked its output there and in general when asked for prose that isn't in the list/Markdown-heavy "LLM style." It's hard to do a confident comparison, but it's seemed bold in arranging the output to flow well, even when that took surgery on the original doc(s). Sometimes the surgery's needed e.g. to connect related ideas the inputs treated as separate, or to ensure it really replies to the request instead of just dumping info that's somehow related to it.

Re: Kimi K2.6: Advancing open-source coding

#66

Post by otabdeveloper4 » Mon, Apr 20, 2026, 5:02 PM UTC

ai_fry_ur_brain wrote: post #57

nickandbro wrote: post #3

Wow, if the benchmarks checkout with the vibes, this could almost be like a Deepseek moment with Chinese AI now being neck and neck with SOTA US lab made models

[flagged]

> Its not anywhere close

Close to what, and how are you measuring?

> nobody in the USA would be spending 7 figures on infrastructure for it

Au contraire, if AI had a moat it would pay for itself. They're funneling capital into infrastructure because they know it can't.

Re: Kimi K2.6: Advancing open-source coding

#67

Post by sigmoid10 » Mon, Apr 20, 2026, 5:04 PM UTC

culi wrote: post #49

elfbargpt wrote: post #26

I've always been surprised Kimi doesn't get more attention than it does. It's always stood out to me in terms of creativity, quality... has been my favorite model for awhile (but I'm far from an authority)

It's also one of the few models that seem capable of drawing an SVG clock https://clocks.brianmoore.com/

Is it? In your link it definitely failed to draw the clock.

Re: Kimi K2.6: Advancing open-source coding

#68

Post by FlyingSnake » Mon, Apr 20, 2026, 5:05 PM UTC

simonw wrote: post #53

Accessed via OpenRouter, this one decided to wrap the SVG pelican in HTML with controls for the animation speed: https://gisthost.github.io/?ecaad98efe0f747e27bc0e0ebc669e94... Transcript and HTML here: https://gist.github.com/simonw/ecaad98efe0f747e27bc0e0ebc669...

At this point drawing these Pelicans must be in the training data sets.

Re: Kimi K2.6: Advancing open-source coding

#69

Post by osti » Mon, Apr 20, 2026, 5:06 PM UTC

konart wrote: post #61

osti wrote: post #36

Earlier quoted context omitted.

Maybe open source == communism

But China is not communist event though the rulling party the word in its name.

Oh i’m fully aware of that lol

Re: Kimi K2.6: Advancing open-source coding

#70

Post by natrys » Mon, Apr 20, 2026, 5:06 PM UTC

johndough wrote: post #51

KaoruAoiShiho wrote: post #48

Earlier quoted context omitted.

Huh, that's not a thing?

The parent poster is probably referring to Kimi-Dev-72B¹, which is a much smaller and older model, while people are probably more familiar with the big and fairly powerful 1100B Kimi-K2.5². [1] https://huggingface.co/moonshotai/Kimi-Dev-72B [2] https://huggingface.co/moonshotai/Kimi-K2.5

Yes it was good for its time, but 10 months old now which is a long time ago in this space. It was also a fine-tune (albeit a good one) of Qwen-2.5 72B.

I wish they did more smaller models. Kimi Linear doesn't really count, it was more of a proof of concept thing.