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

Kimi K2.5 Technical Report [pdf]

github.com

Post reply on HN
Print view View original

11–20 of 146 posts

Re: Kimi K2.5 Technical Report [pdf]

#11

Post by eknkc »

thesurlydev wrote: post #3
zeroxfe wrote: post #2

I've been using this model (as a coding agent) for the past few days, and it's the first time I've felt that an open source model really competes with the big labs. So far it's been able to handle most things I've thrown at it. I'm almost hesitant to say that this is as good as Opus.

Can you share how you're running it?

I've been using it with opencode. You can either use your kimi code subscription (flat fee), moonshot.ai api key (per token) or openrouter to access it. OpenCode works beautifully with the model.

Edit: as a side note, I only installed opencode to try this model and I gotta say it is pretty good. Did not think it'd be as good as claude code but its just fine. Been using it with codex too.

Re: Kimi K2.5 Technical Report [pdf]

#12

Post by zeroxfe »

thesurlydev wrote: post #3
zeroxfe wrote: post #2

I've been using this model (as a coding agent) for the past few days, and it's the first time I've felt that an open source model really competes with the big labs. So far it's been able to handle most things I've thrown at it. I'm almost hesitant to say that this is as good as Opus.

Can you share how you're running it?

Running it via https://platform.moonshot.ai -- using OpenCode. They have super cheap monthly plans at kimi.com too, but I'm not using it because I already have codex and claude monthly plans.

Re: Kimi K2.5 Technical Report [pdf]

#13

Post by epolanski »

gigatexal wrote: post #4
thesurlydev wrote: post #3

Earlier quoted context omitted.

Can you share how you're running it?

Yeah I too am curious. Because Claude code is so good and the ecosystem so just it works that I’m Willing to pay them.

You can plug another model in place of Anthropic ones in Claude Code.

Re: Kimi K2.5 Technical Report [pdf]

#14

Post by zeroxfe »

armcat wrote: post #5
zeroxfe wrote: post #2

I've been using this model (as a coding agent) for the past few days, and it's the first time I've felt that an open source model really competes with the big labs. So far it's been able to handle most things I've thrown at it. I'm almost hesitant to say that this is as good as Opus.

Out of curiosity, what kind of specs do you have (GPU / RAM)? I saw the requirements and it's a beyond my budget so I am "stuck" with smaller Qwen coders.

I'm not running it locally (it's gigantic!) I'm using the API at https://platform.moonshot.ai

Re: Kimi K2.5 Technical Report [pdf]

#17

Post by tgrowazay »

armcat wrote: post #5
zeroxfe wrote: post #2

I've been using this model (as a coding agent) for the past few days, and it's the first time I've felt that an open source model really competes with the big labs. So far it's been able to handle most things I've thrown at it. I'm almost hesitant to say that this is as good as Opus.

Out of curiosity, what kind of specs do you have (GPU / RAM)? I saw the requirements and it's a beyond my budget so I am "stuck" with smaller Qwen coders.

Just pick up any >240GB VRAM GPU off your local BestBuy to run a quantized version.

> The full Kimi K2.5 model is 630GB and typically requires at least 4× H200 GPUs.

Re: Kimi K2.5 Technical Report [pdf]

#18

Post by BeetleB »

zeroxfe wrote: post #14
armcat wrote: post #5

Earlier quoted context omitted.

Out of curiosity, what kind of specs do you have (GPU / RAM)? I saw the requirements and it's a beyond my budget so I am "stuck" with smaller Qwen coders.

I'm not running it locally (it's gigantic!) I'm using the API at https://platform.moonshot.ai

Just curious - how does it compare to GLM 4.7? Ever since they gave the $28/year deal, I've been using it for personal projects and am very happy with it (via opencode).

https://z.ai/subscribe

Re: Kimi K2.5 Technical Report [pdf]

#20

Post by zeroxfe »

epolanski wrote: post #13
gigatexal wrote: post #4

Earlier quoted context omitted.

Yeah I too am curious. Because Claude code is so good and the ecosystem so just it works that I’m Willing to pay them.

You can plug another model in place of Anthropic ones in Claude Code.

That tends to work quite poorly because Claude Code does not use standard completions APIs. I tried it with Kimi, using litellm[proxy], and it failed in too many places.
Post reply on HN