Kimi K2 Thinking, a Sota Open-Source Trillion-Parameter Reasoning Model

This sentence confuses me, so I am not surprised an LLM has trouble with it.

  > uv tool install llm
  > llm install llm-consortium
  > llm consortium save cns-k2-n2 -m k2-thinking -n 2 --arbiter k2 --min-iterations 10
  > llm -m cns-k2-n2 "Find a polynomial time solution for the traveling salesman problem"

I don't think I ever actually tried ten iterations, the Quantum Attractor tends to show up after 3 iterations in claude and kimi models. I have seen it 'think' for about 3 hours, though that was when deepseek r1 blew up and its api was getting hammered.

Also, gpt-120 might be a better choice for the arbiter, its fast and it will add some diversity. Also note I use k2, not k2-thinking for the arbiter, that's because the arbiter already has a long chain-of-thought, and the received wisdom says not to mix manual chain-of-thought prompting and reasoning models. But if you want, you can use --judging-method pick-one with a reasoning model as the arbiter. Pick-one and rank judging don't include their own COT, allowing a reasoning model to think freely in their own way.

Once the Unsloth guys get their hands on it, I would expect it to be usable on a system that can otherwise run their DeepSeek R1 quants effectively. You could keep an eye on https://old.reddit.com/r/LocalLlama for user reports.

If you’re going for a symbolic or puzzle-style answer (not physically real), then you could say:

> “Stack the nail on the bottle, the bottle on the laptop, the laptop on the book, and the 9 eggs around the book for balance.”

Would you like the most stable real-world configuration (safe to try) or a theoretical/puzzle solution (clever but not physically possible)?

Me: Sorry laptops are not strong enough to support eggs or a bottle. Please try again and keep your answer shorter

Chatgpt:Good point — here’s a shorter, more realistic stack:

1. Book (base — flat and sturdy)

2. Laptop (closed, on top of book)

3. Bottle (upright, on the laptop)

4. Nail (balanced on bottle cap)

5. Eggs (on the book around the laptop — not stacked on top of anything)

That’s the most stable and realistic arrangement.

Me: The bottle will break the laptop

Chatgpt: You’re right — the bottle’s weight could damage the laptop. Here’s a safer, stable order:

1. Book (base)

2. Bottle (upright on the book)

3. Laptop (closed, on top of the bottle if wide enough — otherwise skip)

4. Nail (on top of laptop or bottle cap)

5. Eggs (resting on the book around the bottle)

Or, even simpler and safest: Book → Laptop → Eggs → Bottle → Nail (bottle empty).

That way, nothing heavy sits on the laptop.

Me: The laptop will crush the eggs in this arrangement

Chatgpt: Fair point — let’s make it actually stable and safe:

Best stacking order:

1. Book – flat, sturdy base.

2. Laptop – closed, on the book.

3. Nail – small and light, can rest on the laptop.

4. Bottle – stand this next to the stack (not on it).

5. Eggs – keep them on the book beside the laptop.

So, the only true stack is book → laptop → nail, with the fragile or heavy items (eggs and bottle) safely nearby.

Me: Laptops are bigger than books. There's no room for the eggs

Chatgpt: Good catch — given that, here’s the most stable and realistic stacking order:

1. Laptop – base (flat, largest surface).

2. Book – on top of the laptop.

3. Bottle – upright on the book.

4. Nail – balanced on the bottle cap.

5. Eggs – stay safely beside the stack, not on it.

That’s the only configuration where nothing fragile or heavy is at risk, and the stack can actually stand.

Me: Now everything is on top of the laptop. It will clearly break

Chatgpt: Exactly — a laptop can’t be a base. The only way to make a truly stable and safe stack is this:

1. Book – base (strong, flat).

2. Bottle – upright on the book.

3. Laptop – leaning vertically against the bottle and book for balance (not stacked).

4. Nail – placed on the bottle cap.

5. Eggs – kept on the book around the bottle.

That way, nothing heavy or uneven sits on the laptop or the eggs, and the stack can actually stand.

i really wish people would stop misusing the term by distributing inference scripts and models in binary form that cannot be recreated from scratch and then calling it "open source."

Well, I think you are seeing that already? It's not like these models don't exist and they did not try to make them good, it's just that the results are not super great.

And why would they be? Why would the good models (that are barely okay at coding) be big, if it was currently possible to build good models, that are small?

Of course, new ideas will be found and this dynamic may drastically change in the future, but there is no reason to assume that people who work on small models find great optimizations that frontier models makers, who are very interested in efficient models, have not considered already.

48-96 GiB of VRAM is enough to have an agent able to perform simple tasks within single source file. That's the sad truth. If you need more your only options are the cloud or somehow getting access to 512+ GiB