121–130 of 394 posts
Earlier quoted context omitted.
It’s good, but it’s not quite Claude level. And their API has constant capacity issues. Price/quality is absolutely bonkers though. I loaded $40 a few weeks/months ago and I haven’t even gone through half of it.
Why use China model API from China if there are many independent providers available via Openrouter?
Earlier quoted context omitted.
With the previous generation? Yes. With 10T mythos-level models? Not even close.
The psyop continues. Mythos until it’s released is vaporware. Notice how you can try kimi 2.6. Where is the same for mythos?
I'm pretty Kimi is what Cursor uses for their "composer 2" model. Works pretty good as a fallback when Claude runs out, but definitely a downgrade.
Earlier quoted context omitted.
While I'm skeptical of any "beats opus" claims (many were said, none turned out to be true), I still think it's insane that we can now run close-to-SotA models locally on ~100k worth of hardware, for a small team, and be 100% sure that the data stays local. Should be a no-brainer for teams that work in areas where privacy matters.
Even the smaller quantized models which can run on consumer hardware pack in an almost unfathomable amount of knowledge. I don't think I expected to be able to run a 'local Google' in my lifetime before the LLM boom.
There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.
Earlier quoted context omitted.
Maybe open source == communism
Nah, open source means those who do the work own the result. It's supercapitalism.
in capitalism the people with the capital get the profit, not the people who do the work. however, workers are said to benefit too through their salary, just less so
Earlier quoted context omitted.
It’s good, but it’s not quite Claude level. And their API has constant capacity issues. Price/quality is absolutely bonkers though. I loaded $40 a few weeks/months ago and I haven’t even gone through half of it.
Why use China model API from China if there are many independent providers available via Openrouter?
I use OpenCode and the openrouter provider. From opencode I only select the model like kimi-2.6 and have no way of selecting which cloud hosting will receive my request.
https://huggingface.co/moonshotai/Kimi-K2.6 Is this the same model? Unsloth quants: https://huggingface.co/unsloth/Kimi-K2.6-GGUF (work in progress, no gguf files yet, header message saying as much)
A trillion parameters is wild. That's not going to quantize to anything normal folks can run. Even at 1-bit, it's going to be bigger than what a Strix Halo or DGX Spark can run. Though I guess streaming from system RAM and disk makes it feasible to run it locally at <1 token per second, or whatever. GLM 5.1, at 754B parameters, is already beyond any reasonable self-hosting hardware (1-bit quantization is 206GB). Mayb…
Our hope these days seems to be that maybe perhaps possibly High Bandwidth Flash works out. Instead of 4, 8, or maybe more for some highest end drives, having many many many dozens of channels of flash.
Ideally that can be very very near to the inference. PCIe 7.0 is 0.5Tb/s at 16x which is obviously nowhere remotely near enough throughout here. The difficulty is sort of that nand has been trying to be super dense, so as you scale channels you would normally tend to scale nand capacity too, and now instead of a 2tb drive you have a 200tb drive prices way beyond consumer means. Still, I think HBF is perhaps the only shot of the most important thing in computing going from mainframe back to consumer, and of course the models are going to balloon again if this dies hit, probably before consumers ever get a chance.
There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.
Kimi K2.6 seems to struggle most with puzzle/domain-specific and trick-style exactness tasks, where it shows frequent instruction misses and wrong-answer failures.
It is probably a great coding model, but a bit less intelligent overall than SOTAs
[0]: https://aibenchy.com/compare/moonshotai-kimi-k2-6-medium/moo...