LocalLLaMA

localllama@sh.itjust.works

PostsComments

splendoruranium@infosec.pubEnglish · 4 days ago

Local Voiceover/Audiobook generation

6

23

Local Voiceover/Audiobook generation

splendoruranium@infosec.pubEnglish · 4 days ago

6

SmokeyDope@lemmy.worldMEnglish · 6 days ago

MistralAI releases `Magistral`, their first official reasoning models. magistral small 2506 released under apache 2.0 license!

4

29

MistralAI releases `Magistral`, their first official reasoning models. magistral small 2506 released under apache 2.0 license!

SmokeyDope@lemmy.worldMEnglish · 6 days ago

4

10001110101@lemm.eeEnglish · 7 days ago

Current best local models for tool use?

6

11

Current best local models for tool use?

10001110101@lemm.eeEnglish · 7 days ago

6

SmokeyDope@lemmy.worldMEnglish · 9 days ago

Updated guidelines for c/LocaLLama (new rules)

9

28

Updated guidelines for c/LocaLLama (new rules)

SmokeyDope@lemmy.worldMEnglish · 9 days ago

9

pebbles@sh.itjust.worksEnglish · 8 days ago

I'm excited for dots.llm (142BA14B)!

3

12

I'm excited for dots.llm (142BA14B)!

pebbles@sh.itjust.worksEnglish · 8 days ago

3

HumanPerson@sh.itjust.worksEnglish · 9 days ago

What to Integrate With My AI

7

16

What to Integrate With My AI

HumanPerson@sh.itjust.worksEnglish · 9 days ago

7

ikt@aussie.zone

English · 10 days ago

AMD’s Untether AI Deal - Bad Signs for GPU-Driven AI training

semiconductorsinsight.com

35

AMD’s Untether AI Deal - Bad Signs for GPU-Driven AI training

semiconductorsinsight.com

ikt@aussie.zone

English · 10 days ago

ikt@aussie.zone

English · 13 days ago

My AI Skeptic Friends Are All Nuts

news.ycombinator.com

10

My AI Skeptic Friends Are All Nuts

news.ycombinator.com

ikt@aussie.zone

English · 13 days ago

WalnutLum@lemmy.mlEnglish · 16 days ago

Despite record gaming revenues, Nvidia reportedly plans to cut RTX 50 series production to allocate it to new AI hardware

overclock3d.net

2

1

Despite record gaming revenues, Nvidia reportedly plans to cut RTX 50 series production to allocate it to new AI hardware

overclock3d.net

WalnutLum@lemmy.mlEnglish · 16 days ago

2

ThreeJawedChuck@sh.itjust.worksEnglish · 16 days ago

Noob experience using local LLM as a D&D style DM.

5

Noob experience using local LLM as a D&D style DM.

ThreeJawedChuck@sh.itjust.worksEnglish · 16 days ago

ThreeJawedChuck@sh.itjust.worksEnglish · 17 days ago

Don't overlook llama.cpp's rpc-server feature.

1

2

Don't overlook llama.cpp's rpc-server feature.

ThreeJawedChuck@sh.itjust.worksEnglish · 17 days ago

1

thickertoofan@lemm.eeEnglish · 17 days ago

LLMs and their efficiency, can they really replace humans?

5

1

LLMs and their efficiency, can they really replace humans?

thickertoofan@lemm.eeEnglish · 17 days ago

5

SmokeyDope@lemmy.worldMEnglish · 19 days ago

DeepSeek just released updated r1 models with 'deeper and more complex reasoning patterns'. Includes a r1 distilled qwen3 8b model boasting "10% improved performance" over original

1

0

DeepSeek just released updated r1 models with 'deeper and more complex reasoning patterns'. Includes a r1 distilled qwen3 8b model boasting "10% improved performance" over original

SmokeyDope@lemmy.worldMEnglish · 19 days ago

1

suoko@feddit.itEnglish · 20 days ago

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally on your phone. APK

0

2

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally on your phone. APK

suoko@feddit.itEnglish · 20 days ago

0

SmokeyDope@lemmy.worldMEnglish · 21 days ago

Using local model with basic RAG to help reference rules when playing table top game

0

1

Using local model with basic RAG to help reference rules when playing table top game

SmokeyDope@lemmy.worldMEnglish · 21 days ago

0

OpticalMoose@discuss.tchncs.deEnglish · 29 days ago

Intel launches $299 Arc Pro B50 with 16GB of memory, 'Project Battlematrix' workstations with 24GB Arc Pro B60 GPUs

www.tomshardware.com

1

0

Intel launches $299 Arc Pro B50 with 16GB of memory, 'Project Battlematrix' workstations with 24GB Arc Pro B60 GPUs

www.tomshardware.com

OpticalMoose@discuss.tchncs.deEnglish · 29 days ago

1

SmokeyDope@lemmy.worldMEnglish · 29 days ago

Anthropic's 'On the Biology of a LLM' got a massive update: Features fascinating deep dives into how models process information behind the scenes

transformer-circuits.pub

0

1

Anthropic's 'On the Biology of a LLM' got a massive update: Features fascinating deep dives into how models process information behind the scenes

transformer-circuits.pub

SmokeyDope@lemmy.worldMEnglish · 29 days ago

0

thickertoofan@lemm.eeEnglish · 1 month ago

Continuous Thought Machines

0

1

Continuous Thought Machines

thickertoofan@lemm.eeEnglish · 1 month ago

0

🍪CRUMBGRABBER🍪@lemm.eeEnglish · 2 months ago

I'm using open web ui, does anybody else have a better interface?

1

0

I'm using open web ui, does anybody else have a better interface?

🍪CRUMBGRABBER🍪@lemm.eeEnglish · 2 months ago

1

ikt@aussie.zone

English · 2 months ago

Technically correct

1

2

Technically correct

ikt@aussie.zone

English · 2 months ago

1

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.

1 user / day
74 users / week
190 users / month
195 users / 6 months
1 local subscriber
3.21K subscribers
22 Posts
94 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