LocalLLaMA

localllama@sh.itjust.works

PostsComments

Shatur@discuss.tchncs.deEnglish · 5 hours ago

How it actually happened

discuss.tchncs.de

462

How it actually happened

discuss.tchncs.de

Shatur@discuss.tchncs.deEnglish · 5 hours ago

Xer'lodrav@szmer.infoEnglish · 8 hours ago

Qwen3.8 Flash Next (QFN) on Artificial Analysis (AA) Intelligence Index v5.0.1

5

13

Qwen3.8 Flash Next (QFN) on Artificial Analysis (AA) Intelligence Index v5.0.1

Xer'lodrav@szmer.infoEnglish · 8 hours ago

5

Fmstrat@lemmy.worldEnglish · 1 day ago

Fully offline Hermes guide?

5

9

Fully offline Hermes guide?

Fmstrat@lemmy.worldEnglish · 1 day ago

5

Shatur@discuss.tchncs.deEnglish · 2 days ago

Qwalmost there!

discuss.tchncs.de

29

Qwalmost there!

discuss.tchncs.de

Shatur@discuss.tchncs.deEnglish · 2 days ago

Shatur@discuss.tchncs.deEnglish · 1 day ago

Qwen3.8-27B Unsloth Dynamic v3.1 GGUFs out now!

discuss.tchncs.de

42

Qwen3.8-27B Unsloth Dynamic v3.1 GGUFs out now!

discuss.tchncs.de

Shatur@discuss.tchncs.deEnglish · 1 day ago

Avid Amoeba@lemmy.caEnglish · 2 days ago

Nous Research (Hermes) reinforces Western Values

nousresearch.com

9

14

Nous Research (Hermes) reinforces Western Values

nousresearch.com

Avid Amoeba@lemmy.caEnglish · 2 days ago

9

Shatur@discuss.tchncs.deEnglish · 4 days ago

NVIDIA CEO cheated on his wife with a Chinese model

discuss.tchncs.de

720

NVIDIA CEO cheated on his wife with a Chinese model

discuss.tchncs.de

Shatur@discuss.tchncs.deEnglish · 4 days ago

Shatur@discuss.tchncs.deEnglish · 4 days ago

These Chinese models are quite good

discuss.tchncs.de

1

177

These Chinese models are quite good

discuss.tchncs.de

Shatur@discuss.tchncs.deEnglish · 4 days ago

1

Beerus@lemmy.caBanned from communityEnglish · 3 days ago

Luna - Your voice. Your machine. Your Luna

6

21

Luna - Your voice. Your machine. Your Luna

Beerus@lemmy.caBanned from communityEnglish · 3 days ago

6

robertdegallan@lemmy.orgEnglish · 2 days ago

Alibaba + unknown European IT company are cooking something that could crush AI Goliaths

0

4

Alibaba + unknown European IT company are cooking something that could crush AI Goliaths

robertdegallan@lemmy.orgEnglish · 2 days ago

0

Shatur@discuss.tchncs.deEnglish · 6 days ago

Good Luck Getting a Cheap GPU. AMD Is a "Data Center First Company," CEO Says

58

Good Luck Getting a Cheap GPU. AMD Is a "Data Center First Company," CEO Says

Shatur@discuss.tchncs.deEnglish · 6 days ago

Shatur@discuss.tchncs.deEnglish · 7 days ago

Alibaba just posted "The becoming begins", which probably means Qwen4 will be out soon

5

45

Alibaba just posted "The becoming begins", which probably means Qwen4 will be out soon

Shatur@discuss.tchncs.deEnglish · 7 days ago

5

BeefAndPoultry@lemmus.orgEnglish · 5 days ago

PR merged: llama_moe_cache: run missed experts on CPU - Tested on 32GB RAM and 8GB VRAM with Tiel 35b, Gemma 26b, and LFM 24b

3

27

PR merged: llama_moe_cache: run missed experts on CPU - Tested on 32GB RAM and 8GB VRAM with Tiel 35b, Gemma 26b, and LFM 24b

BeefAndPoultry@lemmus.orgEnglish · 5 days ago

3

Canuck@sh.itjust.worksEnglish · 6 days ago

Excellent for local models running via OpenCode

15

Excellent for local models running via OpenCode

Canuck@sh.itjust.worksEnglish · 6 days ago

Nzo@lemmy.zipEnglish · 5 days ago

Eight LLMs in a reality show, week one: Llama nominated Grok as "too expensive to keep around", and now they're trading votes they don't have

inferenceisland.com

18

Eight LLMs in a reality show, week one: Llama nominated Grok as "too expensive to keep around", and now they're trading votes they don't have

inferenceisland.com

Nzo@lemmy.zipEnglish · 5 days ago

Shatur@discuss.tchncs.deEnglish · 6 days ago

Qwen Developers on Twitter: "Qwhen? Qsoon!

5

28

Qwen Developers on Twitter: "Qwhen? Qsoon!

Shatur@discuss.tchncs.deEnglish · 6 days ago

5

leanleft@lemmy.mlEnglish · 5 days ago

old models: tiny chatbot focus

3

4

old models: tiny chatbot focus

leanleft@lemmy.mlEnglish · 5 days ago

3

blam@sh.itjust.worksEnglish · 6 days ago

Local Inference with LLMs · Jacques Mattheij

jacquesmattheij.com

1

15

Local Inference with LLMs · Jacques Mattheij

jacquesmattheij.com

blam@sh.itjust.worksEnglish · 6 days ago

1

Shatur@discuss.tchncs.deEnglish · 7 days ago

New NVIDIA paper says AI models do not always need long context

8

32

New NVIDIA paper says AI models do not always need long context

Shatur@discuss.tchncs.deEnglish · 7 days ago

8

BeefAndPoultry@lemmus.orgEnglish · 6 days ago

llama.cpp v0.9.0

1

20

llama.cpp v0.9.0

BeefAndPoultry@lemmus.orgEnglish · 6 days 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: [email protected]

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.

523 users / day
1.41K users / week
3.54K users / month
3.63K users / 6 months
1 local subscriber
5.63K subscribers
145 Posts
1.46K 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: [email protected]
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)

https://oldsh.itjust.works/

Monitoring Services

lemmy-meter.info