118
If open weight models are the future, U.S. AI companies are going to have a hard time
(www.fastcompany.com)
this post was submitted on 26 Jul 2026
118 points (99.2% liked)
Technology
86628 readers
3879 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
How much RAM do you have?
I can run MiMo 2.5 at about 9 tokens/sec, on 128GB RAM, a 7800 and a 3090 in an SFF rig. That's a fantastic 310B model. I'm requantizing it right now, to see if I can speed it up with Dflash.
Still fantastic models can be run on 64GB or 32GB CPU RAM, as long as you have some GPU. We're awash in sparse models these days.
I've got 128GB RAM + 24GB VRAM on a 4090. I've managed to get a 400B parameter model running on a single board computer with 64GB RAM by using MMAP. But I want to run Kimi K3 locally so I would need a lot more RAM / bandwidth
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 types; 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, which should yield a higher fidelity quantization than a typical Q3 GGUF while taking less RAM..
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 highly 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 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, and it will go obsolete in a month.