LocalLLaMA

localllama@sh.itjust.works

PostsComments

ikt@aussie.zoneEnglish · 3 days ago

NVIDIA - the AI company that sometimes makes graphics cards for gaming

78

NVIDIA - the AI company that sometimes makes graphics cards for gaming

ikt@aussie.zoneEnglish · 3 days ago

ikt@aussie.zoneEnglish · 4 days ago

MMaDA-Parallel: Official Implementation of "MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation"

0

7

MMaDA-Parallel: Official Implementation of "MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation"

ikt@aussie.zoneEnglish · 4 days ago

0

cm0002@no.lastname.nzEnglish · 9 days ago

ollama 0.12.11 Brings Vulkan Acceleration

www.phoronix.com

1

32

ollama 0.12.11 Brings Vulkan Acceleration

www.phoronix.com

cm0002@no.lastname.nzEnglish · 9 days ago

1

Xylight@lemdro.idEnglish · 12 days ago

defend yourself against flock cameras with this simple trick

3

14

defend yourself against flock cameras with this simple trick

Xylight@lemdro.idEnglish · 12 days ago

3

Dark-Alex-17@lemmy.worldEnglish · 16 days ago

Loki - An All-in-One, Batteries Included LLM CLI

0

3

Loki - An All-in-One, Batteries Included LLM CLI

Dark-Alex-17@lemmy.worldEnglish · 16 days ago

0

ikt@aussie.zoneEnglish · 16 days ago

Curl project, swamped with AI slop, finds not all AI is bad

www.theregister.com

0

2

Curl project, swamped with AI slop, finds not all AI is bad

www.theregister.com

ikt@aussie.zoneEnglish · 16 days ago

0

ikt@aussie.zoneEnglish · 20 days ago

In a span of less than 6 months, cumulative downloads of Chinese open models had not only overtaken US models, but began to open a widening lead

0

1

In a span of less than 6 months, cumulative downloads of Chinese open models had not only overtaken US models, but began to open a widening lead

ikt@aussie.zoneEnglish · 20 days ago

0

Xylight@lemdro.idEnglish · 20 days ago

Qwen3 VL support merged into llama.cpp

0

1

Qwen3 VL support merged into llama.cpp

Xylight@lemdro.idEnglish · 20 days ago

0

mudkip@lemdro.idEnglish · 23 days ago

PewDiePie demonstrates $20,000 rig built for vLLM

www.youtube.com

0

1

PewDiePie demonstrates $20,000 rig built for vLLM

www.youtube.com

mudkip@lemdro.idEnglish · 23 days ago

0

knF@lemmy.worldEnglish · 23 days ago

Local VibeCoding (for hobby! :)

0

2

Local VibeCoding (for hobby! :)

knF@lemmy.worldEnglish · 23 days ago

0

eyekaytee@lemmy.worldEnglish · 29 days ago

GPU demand is (~1Mx) distorted by efficiency problems which are being solved

andrewtrask.substack.com

0

2

GPU demand is (~1Mx) distorted by efficiency problems which are being solved

andrewtrask.substack.com

eyekaytee@lemmy.worldEnglish · 29 days ago

0

Xylight@lemdro.idEnglish · 29 days ago

My 8gb vram system as i try to load GLM-4.6-Q0.00001_XXXS.gguf:

media1.tenor.com

0

1

My 8gb vram system as i try to load GLM-4.6-Q0.00001_XXXS.gguf:

media1.tenor.com

Xylight@lemdro.idEnglish · 29 days ago

0

ikt@aussie.zoneEnglish · 1 month ago

AMD Officially Prices Radeon AI PRO R9700 At $1299; Launch Date Announced

0

1

AMD Officially Prices Radeon AI PRO R9700 At $1299; Launch Date Announced

ikt@aussie.zoneEnglish · 1 month ago

0

mudkip@lemdro.idEnglish · 1 month ago

What are your LocalLLaMA "hot takes"?

0

1

What are your LocalLLaMA "hot takes"?

mudkip@lemdro.idEnglish · 1 month ago

0

ThorrJo@lemmy.sdf.orgEnglish · 1 month ago

Why does a Local AI Voice Agent Running on a Super-Cheap Soc Matter?

0

1

Why does a Local AI Voice Agent Running on a Super-Cheap Soc Matter?

ThorrJo@lemmy.sdf.orgEnglish · 1 month ago

0

cm0002@lemmy.zipEnglish · 1 month ago

Valve Developer Contributes Major Improvement To RADV Vulkan For Llama.cpp AI

www.phoronix.com

0

1

Valve Developer Contributes Major Improvement To RADV Vulkan For Llama.cpp AI

www.phoronix.com

cm0002@lemmy.zipEnglish · 1 month ago

0

robber@lemmy.mlEnglish · 1 month ago

Relevance of GPU driver version for inference performance

0

1

Relevance of GPU driver version for inference performance

robber@lemmy.mlEnglish · 1 month ago

0

cm0002@lemmy.zipEnglish · 1 month ago

Tinygrad Gains A Mesa NIR Backend - Initially Supporting NVK/NAK & LLVMpipe Execution - Phoronix

www.phoronix.com

0

1

Tinygrad Gains A Mesa NIR Backend - Initially Supporting NVK/NAK & LLVMpipe Execution - Phoronix

www.phoronix.com

cm0002@lemmy.zipEnglish · 1 month ago

0

cm0002@lemmy.zipEnglish · 1 month ago

ollama Rolls Out Experimental Vulkan Support For Expanded AMD & Intel GPU Coverage

www.phoronix.com

0

1

ollama Rolls Out Experimental Vulkan Support For Expanded AMD & Intel GPU Coverage

www.phoronix.com

cm0002@lemmy.zipEnglish · 1 month ago

0

mudkip@lemdro.idEnglish · 1 month ago

Small models

0

1

Small models

mudkip@lemdro.idEnglish · 1 month ago

0

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
114 users / week
177 users / month
178 users / 6 months
1 local subscriber
3.86K subscribers
55 Posts
29 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