25
submitted 1 week ago* (last edited 1 week ago) by BeefAndPoultry@lemmus.org to c/localllama@sh.itjust.works

It appears to be about as smart as Qwen 3.5 9b but maybe not as good as Ling 3.0 Tiny 8b-a1b

the full LFM3 collection: https://huggingface.co/collections/LiquidAI/lfm3

you are viewing a single comment's thread
view the rest of the comments
[-] panda_abyss@lemmy.ca 2 points 1 week ago* (last edited 1 week ago)

LFM3 1.7B and omni are surprisingly usable.

The official q8 quants are super fast but much much lower quality, so if you can go with the native bf16 weights.

I want to try fine tuning the q8 though for specific tasks, it seems like you cod get a really good balance

this post was submitted on 28 Oct 2026
25 points (93.1% liked)

LocalLLaMA

5571 readers
188 users here now

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.

founded 3 years ago
MODERATORS