[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.

[rubslopes]

Also my experience. I've been going back and forth between Opus and Kimi for the last few days, and, at least for my CRUD webapps, I would say they are both on the same level.

[armcat]

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.

[zeroxfe]

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

[Carrok]

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

[observationist]

API costs on these big models over private hosts tend to be a lot less than API calls to the big 4 American platforms. You definitely get more bang for your buck.

[kristianp]

Note that Kimi K2x is natively 4 bit int, which reduces the memory requirements somewhat.

[tgrowazay]

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.

[timwheeler]

Did you use Kimi Code or some other harness? I used it with OpenCode and it was bumbling around through some tasks that Claude handles with ease.

[zedutchgandalf]

Are you on the latest version? They pushed an update yesterday that greatly improved Kimi K2.5’s performance. It’s also free for a week in OpenCode, sponsored by their inference provider

[thesurlydev]

Can you share how you're running it?

[eknkc]

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.

[zeroxfe]

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.

[JumpCrisscross]

> Can you share how you're running it?

Not OP, but I've been running it through Kagi [1]. Their AI offering is probably the best-kept secret in the market.

[1] https://help.kagi.com/kagi/ai/assistant.html

[explorigin]

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

Requirements are listed.

[indigodaddy]

Been using K2.5 Thinking via Nano-GPT subscription and `nanocode run` and it's working quite nicely. No issues with Tool Calling so far.

[gigatexal]

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.