LocalLLaMA

localllama@sh.itjust.works

PostsComments

lunarwingorg@lemmy.worldEnglish · 2 days ago

LunarWing — self-hostable AI agent framework built in Rust, focused on privacy and real secret management

3

7

LunarWing — self-hostable AI agent framework built in Rust, focused on privacy and real secret management

lunarwingorg@lemmy.worldEnglish · 2 days ago

3

cicadagen@ani.socialEnglish · 7 days ago

Qwen 3.6 27B running at 46 tok/s on an RX 9070 XT (llama.cpp + MTP Speculative Decoding is basically magic)

61

Qwen 3.6 27B running at 46 tok/s on an RX 9070 XT (llama.cpp + MTP Speculative Decoding is basically magic)

cicadagen@ani.socialEnglish · 7 days ago

troed@fedia.io · 7 days ago

Opencode llama-server prefill/generation stats plugin

3

17

Opencode llama-server prefill/generation stats plugin

troed@fedia.io · 7 days ago

3

ikt@aussie.zoneEnglish · 8 days ago

Oops

91

Oops

ikt@aussie.zoneEnglish · 8 days ago

troed@fedia.io · 10 days ago

North Mini Code v1.0 - a Qwen 3.6 35B MoE alternative

5

13

North Mini Code v1.0 - a Qwen 3.6 35B MoE alternative

troed@fedia.io · 10 days ago

5

Schilling2304English · 13 days ago

My models don't have reasoning ability in llama-b9543 server but have in llama-cli

2

7

My models don't have reasoning ability in llama-b9543 server but have in llama-cli

Schilling2304English · 13 days ago

2

HelloRoot@lemy.lolEnglish · 14 days ago

I Put a Datacenter GPU in My Gaming PC for £200

blog.tymscar.com

109

I Put a Datacenter GPU in My Gaming PC for £200

blog.tymscar.com

HelloRoot@lemy.lolEnglish · 14 days ago

potatoguy@mbin.potato-guy.space · 15 days ago

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

0

19

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

potatoguy@mbin.potato-guy.space · 15 days ago

0

robber@lemmy.mlEnglish · 16 days ago

Gemma4 12b released with "unified" approach to multi-modality

21

Gemma4 12b released with "unified" approach to multi-modality

robber@lemmy.mlEnglish · 16 days ago

cm0002@lemy.lolEnglish · 18 days ago

I Tried This Open Source ChatGPT Alternative [Jan AI] on Linux, But Went Back to Ollama

15

I Tried This Open Source ChatGPT Alternative [Jan AI] on Linux, But Went Back to Ollama

cm0002@lemy.lolEnglish · 18 days ago

troed@fedia.io · 22 days ago

Don't skimp on the quant when using MoE

3

30

Don't skimp on the quant when using MoE

troed@fedia.io · 22 days ago

3

pepperfree@sh.itjust.worksEnglish · 23 days ago

Infinity-Parser2 - Multimodal Document Parser

0

7

Infinity-Parser2 - Multimodal Document Parser

pepperfree@sh.itjust.worksEnglish · 23 days ago

0

sp3ctre@feddit.orgEnglish · 29 days ago

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

30

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

sp3ctre@feddit.orgEnglish · 29 days ago

ikt@aussie.zoneEnglish · 1 month ago

DystopiaBench - AI Ethics Stress Test

dystopiabench.com

6

DystopiaBench - AI Ethics Stress Test

dystopiabench.com

ikt@aussie.zoneEnglish · 1 month ago

SuspiciousCarrot78@aussie.zoneEnglish · 1 month ago

Claude? No. Cucumbers? Yes!

3

15

Claude? No. Cucumbers? Yes!

SuspiciousCarrot78@aussie.zoneEnglish · 1 month ago

3

TheCornCollector@piefed.zipEnglish · 1 month ago

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

3

44

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

TheCornCollector@piefed.zipEnglish · 1 month ago

3

BB84@mander.xyzEnglish · 1 month ago

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

4

10

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

BB84@mander.xyzEnglish · 1 month ago

4

SuspiciousCarrot78@aussie.zoneEnglish · 1 month 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 · 1 month ago

SuspiciousCarrot78@aussie.zoneEnglish · 1 month ago

Token Speed visualiser

mikeveerman.github.io

0

9

Token Speed visualiser

mikeveerman.github.io

SuspiciousCarrot78@aussie.zoneEnglish · 1 month ago

0

XiELEd@piefed.socialEnglish · 1 month ago

<8B multilingual models for language learning chatbots

5

9

<8B multilingual models for language learning chatbots

XiELEd@piefed.socialEnglish · 1 month ago

5

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.

14 users / day
123 users / week
446 users / month
1.19K users / 6 months
5 local subscribers
4.83K subscribers
516 Posts
2.81K 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