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

1–10 of 146 posts

Re: Kimi K2.5 Technical Report [pdf]

#2

Post by zeroxfe »

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.

Re: Kimi K2.5 Technical Report [pdf]

#3

Post by thesurlydev »

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?

Re: Kimi K2.5 Technical Report [pdf]

#4

Post by gigatexal »

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?

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.

Re: Kimi K2.5 Technical Report [pdf]

#5

Post by armcat »

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.

Re: Kimi K2.5 Technical Report [pdf]

#7

Post by Carrok »

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.

Not OP but OpenCode and DeepInfra seems like an easy way.

Re: Kimi K2.5 Technical Report [pdf]

#8

Post by explorigin »

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?

https://unsloth.ai/docs/models/kimi-k2.5

Requirements are listed.

Post reply on HN