Exactly, having the mustard toddler pull fable because of, who knows? That burned trust in the west's AI companies.

And there is also the question of what they're doing with the data you send into the models.

Oh that's perfect!

You can't realistically run Kimi (as it's a 1T+ model), but you're set. There's a glut of excellent 120B-300B models for you to choose from.

I'm quantizing MiMo 2.5 specifically to cram into 24GB/128GB as I type this. It's tight, and will use up most of your memory, but it's fantastically smart and plenty fast. The quantization won't finish cooking until tomorrow, but I'll upload it to huggingface then.

But there are others existing quants would fit, like Deepseek Flash IQ3_S: https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF/tree/main/UD-IQ3_S

Or... well, any of these! https://huggingface.co/models?num_parameters=min%3A128B%2Cmax%3A256B&library=gguf&sort=modified

The key for you is to run the ik_llama.cpp fork: https://github.com/ikawrakow/ik_llama.cpp/

It's specifically optimized for hybrid (CPU + GPU) inference on Nvidia desktops; you'll get MUCH faster speeds than mainline llama.cpp or anything based on it. It also supports some more exotic quantization type; as an example, I'm quantizing MiMo 2.5 as a hybrid quant, with the dense layers at IQ6K/Q8_0 and the sparse experts as an IQ3_KT "trellis" quant type. This should yield a higher fidelity quantization than a typical Q3 GGUF while taking less RAM, at the cost of taking forever to quantize and a slight speed hit.

Some other quantization types (like the KS or R4 types) are specifically configured to be fast on CPU.

There are specialized "quant cookers" that make GGUFs specifically for ik_llama.cpp, like:

https://huggingface.co/ubergarm

https://huggingface.co/AesSedai

https://huggingface.co/sigargv/Laguna-M.1-GGUF

https://huggingface.co/models?other=ik_llama.cpp&sort=modified

Mine will be here once I upload it:

https://huggingface.co/Downtown-Case

For anyone else reading this: none of this is applicable to you if you have an AMD/Intel GPU, or an older Nvidia GPU, or less than a certain amount of RAM, or a non AVX2 CPU or... well, there's all sorts of caveats.

The optimal runtime is different for everyone. As an example, exllamav3 is WAY better than llama.cpp on modern Nvidia GPUs until you get above a certain amount of CPU RAM; then using all that RAM for hybrid inference makes more sense. On AMD, different backends work better on different GPUs, and... well, you get the point. Basically all LLM running advice is irrelevant without specifics of your hardware, even this post will be obsolete in a month.

If you're running stuff overnight on a homelab, you can get away with using very large models as agents in CPU RAM.

Another option is a hybrid approach: farm "dumb" privacy-insensitive calls to an API you can subscribe to for like $40 a year, and let your local LLM do the orchestrating. This is what I do: I run MiMo locally, but also farm calls out to the exact same LLM in the cloud when appropriate... And I don't mind one bit. I'm happy to tip them for open sourcing it in the first place.