LocalLLaMA

localllama@sh.itjust.works

PostsComments

copacetic@discuss.tchncs.deEnglish · 15 hours ago

CanIRun.ai — Can your machine run AI models?

2

29

CanIRun.ai — Can your machine run AI models?

copacetic@discuss.tchncs.deEnglish · 15 hours ago

2

variety4me@lemmy.zipEnglish · 22 hours ago

llama.cpp + mcp - docker and more

0

9

llama.cpp + mcp - docker and more

variety4me@lemmy.zipEnglish · 22 hours ago

0

Shimitar@downonthestreet.euEnglish · 2 days ago

How to... (Maybe I am missing something)

4

7

How to... (Maybe I am missing something)

Shimitar@downonthestreet.euEnglish · 2 days ago

4

doodlebob@lemmy.worldEnglish · 8 days ago

Anyone interested in AI radio?

-11

Anyone interested in AI radio?

doodlebob@lemmy.worldEnglish · 8 days ago

humanspiral@lemmy.caEnglish · 15 days ago

A possible hardware solution for ultra speed (73x faster than H200) self hosted small models that is not dependent on RAM

2

5

A possible hardware solution for ultra speed (73x faster than H200) self hosted small models that is not dependent on RAM

humanspiral@lemmy.caEnglish · 15 days ago

2

mudkip@lemdro.idEnglish · 15 days ago

PewDiePie trains his own AI

www.youtube.com

1

4

PewDiePie trains his own AI

www.youtube.com

mudkip@lemdro.idEnglish · 15 days ago

1

vermaterc@lemmy.mlEnglish · 17 days ago

llmfit - find best model that runs on your computer

4

30

llmfit - find best model that runs on your computer

vermaterc@lemmy.mlEnglish · 17 days ago

4

robber@lemmy.mlEnglish · 18 days ago

Smaller qwen3.5 models released

8

40

Smaller qwen3.5 models released

robber@lemmy.mlEnglish · 18 days ago

8

cm0002@lemy.lolEnglish · 21 days ago

ollama 0.17 Released With Improved OpenClaw Onboarding

www.phoronix.com

1

4

ollama 0.17 Released With Improved OpenClaw Onboarding

www.phoronix.com

cm0002@lemy.lolEnglish · 21 days ago

1

ikt@aussie.zoneEnglish · 22 days ago

ggml.ai (the founding team of llama.cpp) joins Hugging Face to ensure the long-term progress of Local AI

0

22

ggml.ai (the founding team of llama.cpp) joins Hugging Face to ensure the long-term progress of Local AI

ikt@aussie.zoneEnglish · 22 days ago

0

humanspiral@lemmy.caEnglish · 23 days ago

Artificial Analysis Intelligence Index and cost benchmarks are useful decision/guidance determinants for which models to use. Analysis for top models.

1

5

Artificial Analysis Intelligence Index and cost benchmarks are useful decision/guidance determinants for which models to use. Analysis for top models.

humanspiral@lemmy.caEnglish · 23 days ago

1

Marvin Damschen@mastodon.nu · 24 days ago

I wrote about running LLMs locally on the Intel Arc Pro B60 GPU previously, where I used Intel's official software stack (llm-scaler / vLLM).

2

16

I wrote about running LLMs locally on the Intel Arc Pro B60 GPU previously, where I used Intel's official software stack (llm-scaler / vLLM).

Marvin Damschen@mastodon.nu · 24 days ago

2

ikt@aussie.zoneEnglish · 26 days ago

I Sold Out for $20 a Month and All I Got Was This Perfectly Generated Terraform

5

I Sold Out for $20 a Month and All I Got Was This Perfectly Generated Terraform

ikt@aussie.zoneEnglish · 26 days ago

ikt@aussie.zoneEnglish · 26 days ago

Qwen3.5: Towards Native Multimodal Agents

1

15

Qwen3.5: Towards Native Multimodal Agents

ikt@aussie.zoneEnglish · 26 days ago

1

mudkip@lemdro.idEnglish · 28 days ago

gpt-oss:20b running in your browser thanks to Transformers.js v4 and ONNX Runtime Web

2

8

gpt-oss:20b running in your browser thanks to Transformers.js v4 and ONNX Runtime Web

mudkip@lemdro.idEnglish · 28 days ago

2

pkjqpg1h@lemmy.zipEnglish · 30 days ago

Minimax M2.5 released

1

15

Minimax M2.5 released

pkjqpg1h@lemmy.zipEnglish · 30 days ago

1

rkd@sh.itjust.worksEnglish · 30 days ago

Have you tried to put together a local health agent?

9

5

Have you tried to put together a local health agent?

rkd@sh.itjust.worksEnglish · 30 days ago

9

mudkip@lemdro.idEnglish · 1 month ago

Qwen-Image-2.0 released: 7B params (massive drop from 20B), unified Gen+Edit, and beats Nano Banana in elo. Weights soon?

files.catbox.moe

1

4

Qwen-Image-2.0 released: 7B params (massive drop from 20B), unified Gen+Edit, and beats Nano Banana in elo. Weights soon?

files.catbox.moe

mudkip@lemdro.idEnglish · 1 month ago

1

humanspiral@lemmy.caEnglish · 1 month ago

openrouter rankings for programming tokens show sharp rise in open models and stagnation of US frontier models

22

openrouter rankings for programming tokens show sharp rise in open models and stagnation of US frontier models

humanspiral@lemmy.caEnglish · 1 month ago

Xylight‮@lemdro.idEnglish · 1 month ago

Qwen 3.5 is coming

3

32

Qwen 3.5 is coming

Xylight‮@lemdro.idEnglish · 1 month ago

3

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.

46 users / day
60 users / week
237 users / month
1.07K users / 6 months
1 local subscriber
4.46K subscribers
424 Posts
2.29K 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