devxyn@sh.itjust.works to

LocalLLaMA@sh.itjust.worksEnglish · 5 days ago

What local, small models are you all using?

47

What local, small models are you all using?

devxyn@sh.itjust.works to

LocalLLaMA@sh.itjust.worksEnglish · 5 days ago

I’m curious about what the consensus is here for which models are used for general purpose stuff (coding assist, general experimentation, etc)

What do you consider the “best” model under ~30B parameters?

Chat

xavierA
link
fedilink
English
arrow-up
1·
5 days ago
Qwen-30 is also my choice when using tools, but i switch to mistral-small for redaction as It manages spanish better IMHO. OSS-120 work great with tools, but it’s slow to unusable on my computer (4060 TI and 64GB RAM). Maybe I’ll try OSS-20, but have readed It is heavilly censored.

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

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.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
101 users / week
380 users / month
1.54K users / 6 months
1 local subscriber
3.65K subscribers
161 Posts
910 Comments
Modlog