top | item 46828706

(no title)

thesurlydev | 1 month ago

Can you share how you're running it?

discuss

order

eknkc|1 month ago

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.

Imustaskforhelp|1 month ago

I tried to use opencode for kimi k2.5 too but recently they changed their pricing from 200 tool requests/5 hour to token based pricing.

I can only speak from the tool request based but for some reason anecdotally opencode took like 10 requests in like 3-4 minutes where Kimi cli took 2-3

So I personally like/stick with the kimi cli for kimi coding. I haven't tested it out again with OpenAI with teh new token based pricing but I do think that opencode might add more token issue.

Kimi Cli's pretty good too imo. You should check it out!

https://github.com/MoonshotAI/kimi-cli

zeroxfe|1 month ago

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.

UncleOxidant|1 month ago

so there's a free plan at moonshot.ai that gives you some number of tokens without paying?

JumpCrisscross|1 month ago

> 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

deaux|1 month ago

Doesn't list Kimi 2.5 and seems to be chat-only, not API, correct?

explorigin|1 month ago

KolmogorovComp|1 month ago

To save everyone a click

> The 1.8-bit (UD-TQ1_0) quant will run on a single 24GB GPU if you offload all MoE layers to system RAM (or a fast SSD). With ~256GB RAM, expect ~10 tokens/s. The full Kimi K2.5 model is 630GB and typically requires at least 4× H200 GPUs. If the model fits, you will get >40 tokens/s when using a B200. To run the model in near full precision, you can use the 4-bit or 5-bit quants. You can use any higher just to be safe. For strong performance, aim for >240GB of unified memory (or combined RAM+VRAM) to reach 10+ tokens/s. If you’re below that, it'll work but speed will drop (llama.cpp can still run via mmap/disk offload) and may fall from ~10 tokens/s to <2 token/s. We recommend UD-Q2_K_XL (375GB) as a good size/quality balance. Best rule of thumb: RAM+VRAM ≈ the quant size; otherwise it’ll still work, just slower due to offloading.

indigodaddy|1 month ago

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|1 month ago

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.

Imustaskforhelp|1 month ago

I tried kimi k2.5 and first I didn't really like it. I was critical of it but then I started liking it. Also, the model has kind of replaced how I use chatgpt too & I really love kimi 2.5 the most right now (although gemini models come close too)

To be honest, I do feel like kimi k2.5 is the best open source model. It's not the best model itself right now tho but its really price performant and for many use cases might be nice depending on it.

It might not be the completely SOTA that people say but it comes pretty close and its open source and I trust the open source part because I feel like other providers can also run it and just about a lot of other things too (also considering that iirc chatgpt recently slashed some old models)

I really appreciate kimi for still open sourcing their complete SOTA and then releasing some research papers on top of them unlike Qwen which has closed source its complete SOTA.

Thank you Kimi!

epolanski|1 month ago

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