LocalLLaMA

localllama@sh.itjust.works

PostsComments

sp3ctre@feddit.orgEnglish · 2 days ago

Your best local LLM for low-VRAM (6GB)?

27

Your best local LLM for low-VRAM (6GB)?

sp3ctre@feddit.orgEnglish · 2 days ago

ikt@aussie.zoneEnglish · 5 days ago

DystopiaBench - AI Ethics Stress Test

dystopiabench.com

6

DystopiaBench - AI Ethics Stress Test

dystopiabench.com

ikt@aussie.zoneEnglish · 5 days ago

SuspiciousCarrot78@aussie.zoneEnglish · 5 days ago

Claude? No. Cucumbers? Yes!

3

13

Claude? No. Cucumbers? Yes!

SuspiciousCarrot78@aussie.zoneEnglish · 5 days ago

3

TheCornCollector@piefed.zipEnglish · 7 days ago

Llama.cpp MTP Support merged - up to 2.5x speed increase

3

41

Llama.cpp MTP Support merged - up to 2.5x speed increase

TheCornCollector@piefed.zipEnglish · 7 days ago

3

BB84@mander.xyzEnglish · 8 days ago

Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution

4

9

Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution

BB84@mander.xyzEnglish · 8 days ago

4

SuspiciousCarrot78@aussie.zoneEnglish · 8 days ago

"The cost of running LLMs is just too damn high"

38

"The cost of running LLMs is just too damn high"

SuspiciousCarrot78@aussie.zoneEnglish · 8 days ago

SuspiciousCarrot78@aussie.zoneEnglish · 9 days ago

Token Speed visualiser

mikeveerman.github.io

0

8

Token Speed visualiser

mikeveerman.github.io

SuspiciousCarrot78@aussie.zoneEnglish · 9 days ago

0

XiELEd@piefed.socialEnglish · 10 days ago

<8B multilingual models for language learning chatbots

4

9

<8B multilingual models for language learning chatbots

XiELEd@piefed.socialEnglish · 10 days ago

4

variety4me@lemmy.zipEnglish · 12 days ago

llama.cpp Multi-Model Server Architecture: ASUS Zenbook UM3504DA

9

14

llama.cpp Multi-Model Server Architecture: ASUS Zenbook UM3504DA

variety4me@lemmy.zipEnglish · 12 days ago

9

ElectricVocalist@jlai.luEnglish · 19 days ago

Gemma4 with MTP was released

1

3

Gemma4 with MTP was released

ElectricVocalist@jlai.luEnglish · 19 days ago

1

Jeena@piefed.jeena.netEnglish · 19 days ago

Good translation models which fit on a smartphone?

21

Good translation models which fit on a smartphone?

Jeena@piefed.jeena.netEnglish · 19 days ago

tristynalxander@mander.xyzEnglish · 20 days ago

AI-Editor in LibreOffice Writer?

3

16

AI-Editor in LibreOffice Writer?

tristynalxander@mander.xyzEnglish · 20 days ago

3

ikt@aussie.zoneEnglish · 24 days ago

a little locallama game theory ...game

5

9

a little locallama game theory ...game

ikt@aussie.zoneEnglish · 24 days ago

5

ikt@aussie.zoneEnglish · 25 days ago

Mistral Medium 3.5 released

1

19

Mistral Medium 3.5 released

ikt@aussie.zoneEnglish · 25 days ago

1

hendrik@palaver.p3x.deEnglish · 25 days ago

Is there any good general AI-Agent /workflow platform which isn't vibe-coded?

7

18

Is there any good general AI-Agent /workflow platform which isn't vibe-coded?

hendrik@palaver.p3x.deEnglish · 25 days ago

7

variety4me@lemmy.zipEnglish · 26 days ago

would you laugh at me if I ran gemma-4-26b on a 4 core Xeon, with 32GB RAM, no GPU?

2

29

would you laugh at me if I ran gemma-4-26b on a 4 core Xeon, with 32GB RAM, no GPU?

variety4me@lemmy.zipEnglish · 26 days ago

2

robber@lemmy.mlEnglish · 26 days ago

llama.cpp: don't sleep on --split-mode tensor

0

17

llama.cpp: don't sleep on --split-mode tensor

robber@lemmy.mlEnglish · 26 days ago

0

Yerbouti@sh.itjust.worksEnglish · 27 days ago

Noob here: Why is Google making Gemma open-source?

14

Noob here: Why is Google making Gemma open-source?

Yerbouti@sh.itjust.worksEnglish · 27 days ago

hok@lemmy.dbzer0.comEnglish · 27 days ago

Which open models are actually good at agentic coding?

9

20

Which open models are actually good at agentic coding?

hok@lemmy.dbzer0.comEnglish · 27 days ago

9

ikt@aussie.zoneEnglish · 27 days ago

BullshitBench Viewer - BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

petergpt.github.io

2

12

BullshitBench Viewer - BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

petergpt.github.io

ikt@aussie.zoneEnglish · 27 days ago

2

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: !localllama@sh.itjust.works

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.

4 users / day
105 users / week
387 users / month
1.05K users / 6 months
1 local subscriber
4.74K subscribers
181 Posts
1.31K Comments
Modlog

sh.itjust.works

A bilingual (EN/FR) general-purpose instance located in eastern Canada! Powered by 99% renewable energy! Everyone is welcome eh.

Useful Links

Lemmy Getting Started Guide
Official Lemmy Support
Search communities across all lemmy instance
sh.itjust.works meta discussion community: !main@sh.itjust.works
sh.itjust.works Matrix chat: https://matrix.to/#/#sh.itjust.works:matrix.org

Donations

Rules:

Be respectful. Everyone should feel welcome here.
No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
No Ads / Spamming.
No pornography.

Règles :

Soyez respectueux. Tout le monde doit se sentir le bienvenu ici.
Pas de bigoterie - y compris le racisme, le sexisme, le capacitisme, l’homophobie, la transphobie ou la xénophobie.
Pas de publicités / Pas de spam.
Pas de pornographie.

Fediseer

Other UI options (more to come)

Monitoring Services

lemmy-meter.info