waiting for - "Running Kimi K3 on X years old hardware".
Kimi K3: Open Frontier Intelligence
461–470 of 1001 posts
Re: Kimi K3: Open Frontier Intelligence
#462Earlier quoted context omitted.
Nah: https://www.youtube.com/watch?v=LSlV206xPqM These real world examples show it's one tier away.
These "real world" examples are nothing like the way I use LLMs from within a harness. GPT 5.6 Sol and Fable are clearly more impressive, but how does this translate to interactive agent use, or use under an agent orchestration framework?
This is a question I am going to get an answer tomorrow with evals. Extremely interesting...
Re: Kimi K3: Open Frontier Intelligence
#463Earlier quoted context omitted.
It's like reading Anthropic's obituary.
Fable is by Anthropic, and this is too expensive, GLM 5.2 is roughly the same quality at a much cheaper price. (I mantain a client with llama.cpp and 101 models across 14 companies by http)
GLM has issues with tool calls and nested JSON and it wastes tokens pretty often. I see it being a bit above half the price of Opus in a bit more complex eval tasks. With some RL you could probably get the tool calls sorted and the price down.
Re: Kimi K3: Open Frontier Intelligence
#464> Chip Design > As an early proof of concept, Kimi K3 designed a chip to serve a nano model built on its own architecture. In a single 48-hour autonomous run, K3 built, optimized, and verified the chip using open-source EDA tools on the Nangate 45nm library. Within 4 mm², the chip closes timing at 100 MHz and sustains over 8,700 tokens/s decode throughput in simulation, packing 1.46M standard cells, 0.277 MB of SRAM,…
I had a thought a while back: sell large local models burned onto fused compute / ROM chips. Like cartridges for old game consoles. Slot (or probably plug into USB-C) and go. It’s an ASIC with the model wired into it so it’s very low power and fast. I’d buy these. Say $100 for a frontier class model. Maybe more.
How very Cyberdyne.
Re: Kimi K3: Open Frontier Intelligence
#465Earlier quoted context omitted.
GLM is actually quite expensive in actual practice because it's not very token efficient. I've yet to find a way to run it on a monthly sub reliably for cheaper than Codex. Neuralwatt was cheap (but slow) but they cranked their price. Ollama monthly sub is speedy but doesn't offer a lot of quota. Right now unless you're paying by the token, there's no cost based reason to use the open weight models for daily coding w…
I know GLM is relatively expensive and so is Kimi, in comparison to those DeepSeek V4 pro and flash are a godsend and are absolutely good value.
I use V4 flash as my personal agent. It categorizes documents, organizes my calendar, searches information etc. for pennies. Amazing model.
Not very good for programming though.
Re: Kimi K3: Open Frontier Intelligence
#466Some official benchmark numbers posted in Chinese social media (I am sure they will publish an English blogpost later too): https://mp.weixin.qq.com/s/V4xhEIy8xDXSMDPrPkmUAQ Generally looks like a Sol/Fable tier model, better across the board than Opus 4.8. (Edit) English blogpost is up now: https://www.kimi.com/blog/kimi-k3
[flagged]
[dead]
Re: Kimi K3: Open Frontier Intelligence
#467[dead]
Re: Kimi K3: Open Frontier Intelligence
#468Earlier quoted context omitted.
This is weird and reactionary. Lots of organizations are continuing to refuse to use chinese models due to security and IP concerns. Anthropic/american models aren't going anywhere anytime soon.
> Lots of organizations are continuing to refuse to use chinese models due to security and IP concerns This is such a common omission: the Chinese models are open, you can host them yourself on your premises. So privacy and independence.
Good luck hosting 2.8T params yourself. A box capable of this at a useful performance level is at least $100k.
Re: Kimi K3: Open Frontier Intelligence
#469Some official benchmark numbers posted in Chinese social media (I am sure they will publish an English blogpost later too): https://mp.weixin.qq.com/s/V4xhEIy8xDXSMDPrPkmUAQ Generally looks like a Sol/Fable tier model, better across the board than Opus 4.8. (Edit) English blogpost is up now: https://www.kimi.com/blog/kimi-k3
It's like reading Anthropic's obituary.
Certainly for their IPO, anyway
Re: Kimi K3: Open Frontier Intelligence
#470Earlier quoted context omitted.
It's like reading Anthropic's obituary.
This is weird and reactionary. Lots of organizations are continuing to refuse to use chinese models due to security and IP concerns. Anthropic/american models aren't going anywhere anytime soon.
This is apparently Open Weights, so no reason Amazon can't serve it alongside GLM which they already do.