Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
cross-posted from: https://piefed.zip/c/fosai/p/958141/30b-a3b-glm-4-7-flash-released
Small/fast model with MIT license for local use.
Benchmarks look good for the size. But IMO these smaller models aren’t consistent enough to live up to their promises.
Oo. I use Qwen3-30B-A3B-Thinking-2507 as my generic "workhorse" local LLM, so this looks like it might be a nice upgrade with exactly the same basic specs. I'll try it out.
Anyone get this working in llama.cpp yet?
I know flash attention and PyTorch have patchy support.
And that PR is already shipped, the community works fast!
Edit: I tried a 4bit quant of this model and it is probably one of the worst/most benchmaxxed models I've seen. Reasoning is quite bad, recall of facts is bad, reading and digesting content is bad. But it is fast.
Unfortunately, the AI community prefers rushed buggy development over proper, tested releases, so the quants and maybe the PR weren’t fully working.
As of 3 hours ago, unsloth was still updating their quants and guide. I don’t have time to test now but I wouldn’t judge the base model performance in the first few days when the bugs are still being worked out.
They also recommend some unconventional parameters in the Unsloth guide.
It could also be that the model is truly shit of course.
Edit I just took a look at the llama.cpp repo and there are still issues with the implementation as well.
