LocalLLaMA

localllama@sh.itjust.works

PostsComments

SirDimples@programming.devEnglish · 22 hours ago

Qwen3.8-2.4T-A95B Open Weights Released!

2

31

Qwen3.8-2.4T-A95B Open Weights Released!

SirDimples@programming.devEnglish · 22 hours ago

2

SirDimples@programming.devEnglish · 22 hours ago

Qwen3.8-27B drops two days from now

1

41

Qwen3.8-27B drops two days from now

SirDimples@programming.devEnglish · 22 hours ago

1

ZephyrXero@lemmy.worldEnglish · 2 days ago

A custom Qwen 35B that can run on just a 4GB GPU

microflare.bearblog.dev

0

12

A custom Qwen 35B that can run on just a 4GB GPU

microflare.bearblog.dev

ZephyrXero@lemmy.worldEnglish · 2 days ago

0

leanleft@lemmy.mlEnglish · 3 days ago

model : Ling-3.0-tiny (8b)

1

10

model : Ling-3.0-tiny (8b)

leanleft@lemmy.mlEnglish · 3 days ago

1

SirDimples@programming.devEnglish · 10 days ago

GLM-5.3 Imminent drop

5

19

GLM-5.3 Imminent drop

SirDimples@programming.devEnglish · 10 days ago

5

leanleft@lemmy.mlEnglish · 13 days ago

model: deepseek-moe-16b

0

4

model: deepseek-moe-16b

leanleft@lemmy.mlEnglish · 13 days ago

0

leanleft@lemmy.mlEnglish · 19 days ago

how many models have you collected locally?

3

3

how many models have you collected locally?

leanleft@lemmy.mlEnglish · 19 days ago

3

Shifu@lemmy.worldEnglish · 29 days ago

Spent two weeks on a kernel that benchmarked 29x faster. End to end it's maybe 6-10%, and it's not even wired in yet.

3

16

Spent two weeks on a kernel that benchmarked 29x faster. End to end it's maybe 6-10%, and it's not even wired in yet.

Shifu@lemmy.worldEnglish · 29 days ago

3

catch88@sh.itjust.worksEnglish · 1 month ago

I gave my local LLM agent a face — an avatar frontend with an "emotion-beat" output contract (open-source)

sh.itjust.works

8

-5

I gave my local LLM agent a face — an avatar frontend with an "emotion-beat" output contract (open-source)

sh.itjust.works

catch88@sh.itjust.worksEnglish · 1 month ago

8

Shifu@lemmy.worldEnglish · 1 month ago

BitNet b1.58-2B-4T at 36 tok/s on Xeon - pure C99, no Python/BLAS, single binary for ternary + GGUF

0

4

BitNet b1.58-2B-4T at 36 tok/s on Xeon - pure C99, no Python/BLAS, single binary for ternary + GGUF

Shifu@lemmy.worldEnglish · 1 month ago

0

leanleft@lemmy.mlEnglish · 1 month ago

alibaba-pai/DistillQwen-ThoughtY-4B

0

10

alibaba-pai/DistillQwen-ThoughtY-4B

leanleft@lemmy.mlEnglish · 1 month ago

0

leo@sh.itjust.worksEnglish · 2 months ago

Local LLM Inference Optimization: The Complete Guide

2

32

Local LLM Inference Optimization: The Complete Guide

leo@sh.itjust.worksEnglish · 2 months ago

2

lunarwingorg@lemmy.worldEnglish · 2 months ago

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

4

5

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

lunarwingorg@lemmy.worldEnglish · 2 months ago

4

robber@lemmy.mlEnglish · 2 months ago

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

1

14

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

robber@lemmy.mlEnglish · 2 months ago

1

pepperfree@sh.itjust.worksEnglish · 3 months ago

Infinity-Parser2 - Multimodal Document Parser

0

6

Infinity-Parser2 - Multimodal Document Parser

pepperfree@sh.itjust.worksEnglish · 3 months ago

0

BB84@mander.xyzEnglish · 3 months ago

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

2

5

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

BB84@mander.xyzEnglish · 3 months ago

2

robber@lemmy.mlEnglish · 4 months ago

llama.cpp: don't sleep on --split-mode tensor

0

11

llama.cpp: don't sleep on --split-mode tensor

robber@lemmy.mlEnglish · 4 months ago

0

Yerbouti@sh.itjust.worksEnglish · 4 months ago

Noob here: Why is Google making Gemma open-source?

4

Noob here: Why is Google making Gemma open-source?

Yerbouti@sh.itjust.worksEnglish · 4 months ago

hok@lemmy.dbzer0.comEnglish · 4 months ago

Which open models are actually good at agentic coding?

7

13

Which open models are actually good at agentic coding?

hok@lemmy.dbzer0.comEnglish · 4 months ago

7

Fmstrat@lemmy.worldEnglish · 4 months ago

Intel B70: LLama.cpp SYCL vs LLama.cpp OpenVino vs LLM-Scaler

0

5

Intel B70: LLama.cpp SYCL vs LLama.cpp OpenVino vs LLM-Scaler

Fmstrat@lemmy.worldEnglish · 4 months 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.

83 users / day
60 users / week
134 users / month
470 users / 6 months
1 local subscriber
5.02K subscribers
354 Posts
975 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)

https://oldsh.itjust.works/

Monitoring Services

lemmy-meter.info