LocalLLaMA

2884 readers

36 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.

founded 2 years ago

MODERATORS

pax@sh.itjust.works

SkySyrup@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works

[April 2025] Which model are you using? (aussie.zone)

submitted 5 days ago by Eyekaytee@aussie.zone to c/localllama@sh.itjust.works

9 comments fedilink hide all child comments

Just thinking about making this a monthly post, which model are you using? what are the positives and negatives?

top 9 comments

sorted by: hot top controversial new old

[–] OpticalMoose@discuss.tchncs.de 8 points 5 days ago (1 children)

I mainly use Llama-3-8B abliterated for everyday questions, and DeepSeek-Coder-V2-Lite for programming/Linux stuff.

[–] Eyekaytee@aussie.zone 2 points 2 days ago

Using DeepSeek-Coder-V2-Lite now, it's awesome!

[–] Audalin@lemmy.world 5 points 5 days ago (2 children)

QWQ-32B for most questions, llama-3.1-8B for agents. I'm looking for new models to replace them though, especially the agent one.

Want to test the new GLM models, but I'd rather wait for llama.cpp to definitely fix the bugs with them first.

[–] Eyekaytee@aussie.zone 2 points 2 days ago* (last edited 2 days ago) (1 children)

Want to test the new GLM models

Which models are you referring to? These: https://github.com/THUDM/GLM-4 ?

[–] Audalin@lemmy.world 2 points 2 days ago

That's the ones, the 0414 release.

[–] weker01@sh.itjust.works 4 points 5 days ago* (last edited 5 days ago)

GLM? I feel like every other day there is a new abbreviation :(

[–] Smokeydope@lemmy.world 5 points 5 days ago* (last edited 5 days ago)

I have been using deephermes daily. I think CoT reasoning is so awesome and such a game changer! It really helps the model give better answers especially for hard logical problems. But I don't want it all the time especially on an already slow model. Being able to turn it on and off wirhout switching models is awesome. Mistral 24b deephermes is relatively uncensored, powerful and not painfully slow on my hardware. a high quant of llama 3.1 8b deephermes is able to fit entirely on my 8gb vram.

[–] eurisko@lemmy.ca 6 points 5 days ago

I find that for the purpose of my projects (narrative building, tabletop rpg simulation) gemma3:14b (with low temperature) works perfectly to create consistent psychological overviews.

[–] weker01@sh.itjust.works 4 points 5 days ago

Fallen Gemma. The writing style is really good and it can keep relatively persistent personalities. On the other hand it's stupid af compared to other recent models and even the vanilla Gemma 3.