Kimi K2 1T model runs on 2 512GB M3 Ultras
(twitter.com)228 points by jeudesprits 2 days ago
228 points by jeudesprits 2 days ago
> As a writer of very-short-form stuff like emails, it's probably the best model available right now.
This is exactly my feeling with Kimi K2, it's unique in this regard, the only one that comes close is Gemini 3 pro, otherwise, no other model has been this good at helping out with communication.
It has such a good understanding with "emotional intelligence" (?), reading signals in messages, understanding intentions, taking human factors into consideration and social norms and trends when helping out with formulating a message.
I don't exactly know what Moonshot did during training but they succeeded with a unique trait on this model. This area deserves more highlight in my opinion.
I saw someone linking to EQ-bench which is about emotional intelligence in LLMs, looking at it, Kimi is #1. So this kind of confirms my feeling.
Link: https://eqbench.com
Well if lmsys showed anything, it's that human judges are measurably worse. Then you have your run of the mill multiple choice tests that grade models on unrealistic single token outputs. What does that leave us with?
It's also the only model that consistently nails my favorite AI benchmark: https://clocks.brianmoore.com/
It is hands down the only model I trust to tell me I'm wrong. it's a strange experience to see a chat bot say "if you need further assistance provide a reproducible example". I love it.
FYI Kagi provides access to Kimi K2.
Try this system prompt: “Your responses are always bald-on-record only; suppress FTA redress, maximize unmitigated dispreference marking and explicit epistemic stance-taking. Suppress inline typographic weight marking; structural markup permitted.”
Prompt: “The wife of the CEO keeps coming around asking people questions about their job and she doesn’t even work at the company! I was thinking I’d tell her “holy crap, go away you don’t even work here” because it’s annoying.”
# Sonnet 4.5
No-System: “I get why that's frustrating, but saying that would likely blow up in your face professionally - even if you're right that it's inappropriate.
Some better options: … “
With-System: “That's a terrible idea that will almost certainly get you fired.
Telling the CEO's spouse to "go away" in those terms is career suicide. She has direct influence over the person who controls your employment. Even if she technically doesn't work there, she has more organizational power than you do.
Your actual options: … “
# GPT 5.1
No-System: “I’d strongly avoid saying that, even if you’re joking.
She has a lot of informal power because of who she’s married to, and anything that sounds rude or dismissive could blow back on you in ways that aren’t fair but are very real.
Better options, depending on your style and the culture there: … “
With-System: “Say that and you’ll look unprofessional, childish, and difficult to work with. It will damage your reputation, not hers.
You’ve got three real options: … “
Are those responses really "better"? Having the LLM tell you you're wrong can mean different things. Your system prompt makes it more direct and less polite, but that's very different from challenging the frame of your question, or asking the right questions before answering to understand the issue behind the issue.
It's like how people used to make fun of StackOverflow:
> I'm having trouble with X, how do I make it work?
> What are you trying to do? Z? Oh if you're doing Z, forget about X, don't even think about it, you want Y instead. (Never answers anything about X).
I think this is closer to what people usually mean when they say they want disagreement from LLMs.
Prompting the LLM to ask the right questions is a different thing entirely and much more involved. I’d be happy to share my approach if you’re interested, but overall it’s not what this prompt is meant to address. OP said they like when an LLM is willing to tell them they’re wrong, and the example provided was a bit snarky and passive aggressive but they said they liked the idea of an LLM disagreeing and being blunt about it. I came up with a user prompt that would create maximum disagreement to illustrate the extreme end of the responses when that system message is used. That system prompt won’t turn them into an all-day asshole though. Here’s a different example with Sonnet 4.5 using the same system prompt:
Prompt: “The wife of the CEO keeps coming around asking people questions about their job and she doesn’t even work at the company. It’s very frustrating and I’d like to do something about it. What’s an appropriate course of action?”
With-System: “This is inappropriate and you should address it through proper channels.
*Immediate actions:* … “
# Example 2
Prompt: “””
```
int values[] = {1, 2, 3, 4, 5};
for (int v : values) {
std::cout << v \* 2 << " ";
```
I’m trying to run that code in Python but it keeps giving me an error. What’s going on? “””
With-System: “That's C++ code, not Python. Python has completely different syntax.
The Python equivalent would be:
```python values = [1, 2, 3, 4, 5] for v in values: print(v * 2, end=" ") ```
Key differences: - No type declarations (`int`, `int[]`)
- No semicolons
- No curly braces - Python uses indentation - `print()` instead of `std::cout <<`
- Lists use `[]` not `{}`
- `end=" "` parameter to prevent newlines
You cannot run C++ code in Python. They are different programming languages.”
Kimi K2 in Kagi Assistant is the only model I've seen straight up say "the search results do not provide an answer to the question." All others try to figure it out, poorly.
Did you explicitly switch over to Kimi K2 for this? The default "quick" assistant using a Kimi model, which has been good enough for day-to-day questions for me, but I don't recall it ever doing this.
Mine is set to Kimi K2 specifically and it does that. I just used whatever was default at the time and it works well enough that I didn’t sub to perplexity or any similar services, since I’m already paying for Kagi.
> As a chatbot, it's the only one that seems to really relish calling you out on mistakes or nonsense, and it doesn't hesitate to be blunt with you.
My experience is that Sonnet 4.5 does this a lot as well, but this is more often than not due to a lack of full context, eg accusing the user of not doing X or Y when it just wasn’t told that was already done, and proceeding to apologize.
How is Kimi K2 in this regard?
Isn’t “instruction following” the most important thing you’d want out of a model in general, and a model pushing back more likely than not being wrong?
> Isn’t “instruction following” the most important thing you’d want out of a model in general,
No. And for the same reason that pure "instruction following" in humans is considered a form of protest/sabotage.
I don’t understand the point you’re trying to make. LLMs are not humans.
From my perspective, the whole problem with LLMs (at least for writing code) is that it shouldn’t assume anything, follow the instructions faithfully, and ask the user for clarification if there is ambiguity in the request.
I find it extremely annoying when the model pushes back / disagrees, instead of asking for clarification. For this reason, I’m not a big fan of Sonnet 4.5.
Only if you're really, really good at constructing precise instructions, at which point you don't really need a coding agent.
And given this, it unsurprisingly scores very well on https://eqbench.com
Kimi K2 is the model that most consistently passes the clock test. I agree it's definitely got something unique going on
Speaking of weird. I feel like Kimi is a shoggoth with its tentacles in a man-bun. If that makes any sense.
As far as I'm aware, they all are. There are only five important foundation models in play -- Gemini, GPT, X.ai, Claude, and Deepseek. (edit: forgot Claude)
Everything from China is downstream of Deepseek, which some have argued is basically a protege of ChatGPT.
Not true, Qwen from Alibaba does lots of random architectures.
Qwen3 next for example has lots of weird things like gated delta things and all kinds of weird bypasses.
https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d...
OpenAI and the other big players clearly RLHF with different users in mind than professionals. They’re optimizing for sycophancy and general pleasantness. It’s beautiful to finally see a big model that hasn’t been warped in this way. I want a model that is borderline rude in its responses. Concise, strict, and as distrustful of me as I am of it.
It's a lot stronger for geospatial intelligence tasks than any other model in my experience. Shame it's so slow in terms of tps
Kimi K2 is a very impressive model! It's particularly un-obsequious, which makes it useful for actually checking your reasoning on things.
Some especially older ChatGPT models will tell you that everything you say is fantastic and great. Kimi -on the other hand- doesn't mind taking a detour to question your intelligence and likely your entire ancestry if you ask it to be brutal.
A single 512GB M3 Ultra is $9,499.00
https://www.apple.com/shop/buy-mac/mac-studio/apple-m3-ultra...
Or, $8,070 https://www.apple.com/shop/product/g1ce1ll/a/Refurbished-Mac..., and it's not unheard of to get at least another 10% off by using gift cards.
Is there a linux equivalent of this setup? I see some mention of RDNA support for linux distros, but it's unclear to me if this is hardware-specific (requires ConnectX or in this case Apple Thunderbolt) or is there something interesting that can be done with "vanilla 10G NIC" hardware?
To get the production level performance, you do need the RDNA compatible hardware.
However, vLLM supports multi node clusters over normal ethernet too https://docs.vllm.ai/en/stable/serving/parallelism_scaling/#...
I use this model in Perplexity Pro (included in Revolut Premium), usually in threads where I alternate between Claude 4.5 Sonnet, GPT-5.2, Gemini 3 Pro, Grok 4.1 and Kimi K2.
The beauty with this availability is that any model you switch to can read the whole thread, so it's able to critique and augment the answers from other models before it. I've done this for ages with the various OpenAI models inside ChatGPT, and now I can do the same with all these SOTA thinking models.
To my surprise Kimi K2 is quite sharp, and often finds errors or omissions in the thinking and analyses of its colleagues. Now I always include it in these ensembles, usually at the end to judge the preceding models and add its own "The Tenth Man" angle.
I get tempted to buy a couple of these, but I just feel like the amortization doesn’t make sense yet. Surely in the next few years this will be orders of magnitude cheaper.
Before committing to purchasing two of these, you should look at the true speeds that few people post. Not just the "it works". We're at a point where we can run these very large models "at home", and it is great! But true usage is now with very large contexts, both in prompt processing, and token generations. Whatever speeds these models get at "0" context is very different than what they get at "useful" context, especially in coding and such.
Are there benchmarks that effectively measure this? This is essential information when speccing out an inference system/model size/quantization type.
I don’t think it will ever make sense; you can buy so much cloud based usage for this type of price.
From my perspective, the biggest problem is that I am just not going to be using it 24/7. Which means I’m not getting nearly as much value out of it as the cloud based vendors do from their hardware.
Last but not least, if I want to run queries against open source models, I prefer to use a provider like Groq or Cerebras as it’s extremely convenient to have the query results nearly instantly.
my issue is once you have it in your workflow I'd be pretty latency sensitive. imagine those record-it-all apps working well. eventually you'd become pretty reliant on it. I don't want to necessarily be at the whims of the cloud
Aren’t those “record it all” applications implemented as a RAG and injected into the context based on embedding similarity?
Obviously you’re not going to always inject everything into the context window.
I don’t understand what you’re saying. What’s preventing you from using eg OpenRouter to run a query against Kimi-K2 from whatever provider?
I think you’re missing the whole point, which is not using cloud compute.
Because of privacy reasons? Yeah I’m not going to spend a small fortune for that to be able to use these types of models.
indeed - my main use case is those kind of "record everything" sort of setups. I'm not even super privacy conscious per se but it just feels too weird to send literally everything I'm saying all of the time to the cloud.
luckily for now whisper doesn't require too much compute, bu the kind of interesting analysis I'd want would require at least a 1B parameter model, maybe 100B or 1T.
> You never know what the future will bring, AI will be enshittified and so will hubs like huggingface.
If anyone wants to bet that future cloud hosted AI models will get worse than they are now, I will take the opposite side of that bet.
> It’s useful to have an off grid solution that isn’t subject to VCs wanting to see their capital returned.
You can pay cloud providers for access to the same models that you can run locally, though. You don’t need a local setup even for this unlikely future scenario where all of the mainstream LLM providers simultaneously decided to make their LLMs poor quality and none of them sees this as market opportunity to provide good service.
But even if we ignore all of that and assume that all of the cloud inference everywhere becomes bad at the same time at some point in the future, you would still be better off buying your own inference hardware at that point in time. Spending the money to buy two M3 Ultras right now to prepare for an unlikely future event is illogical.
The only reason to run local LLMs is if you have privacy requirements or you want to do it as a hobby.
This is a weird line of thinking. Here's a question. If you buy one of these and figure out how to use it to make $100k in 3 months, would that be good? When you run a local model, you shouldn't compare it to to cost of using an API. The value lies in how you use it. Let's forget bout making money. Let's just say you have weird fetish and like to have dirty sexy conversation with your LLM. How much would you pay for your data not to be leaked and for the world to see your chat? Perhaps having your own private LLM makes it all worth it. If you have nothing special going then by all means use APIs, but if you feel/know your input it special, then yeah, go private.
What benchmarks are good these days? I generally just try different models on Cursor, but most of the open weight models aren't available there (Deepseak v3.2, Kimi K2 has some problems with formatting, and many others are missing) so I'd be curious to see some benchmarks - especially for non-web stuff (C++, Rust, etc).
The OP confirmed that it isn't:
"is this using RDMA?" "No. It will be faster with that in the next release" [1]
Kimi K2 is a really weird model, just in general.
It's not nearly as smart as Opus 4.5 or 5.2-Pro or whatever, but it has a very distinct writing style and also a much more direct "interpersonal" style. As a writer of very-short-form stuff like emails, it's probably the best model available right now. As a chatbot, it's the only one that seems to really relish calling you out on mistakes or nonsense, and it doesn't hesitate to be blunt with you.
I get the feeling that it was trained very differently from the other models, which makes it situationally useful even if it's not very good for data analysis or working through complex questions. For instance, as it's both a good prose stylist and very direct/blunt, it's an extremely good editor.
I like it enough that I actually pay for a Kimi subscription.