| Topics | Replies | Author | Score | Last Post |
|---|
|
|
what is your selfhosted local LLM stack?
|
8 |
Alvaro |
19 |
» |
|
|
If documents added as context to GPT4all take too long to embed, try changing the embedding device in the settings
|
0 |
Auster |
2 |
» |
|
|
K2 Horizon: Open-Source Model Family
(ifm.ai)
|
0 |
TheCornCollector |
8 |
» |
|
|
We gave six LLMs a fact from 2025. Two "corrected" us with a fact from 2021, and the table adopted the stale number as its standard of rigour
(h2aichat.com)
|
13 |
h2aichat_com |
-7 |
» |
|
|
We fact-checked 41 debates between different LLMs and struck through every fabrication, without editing a word
(lemmy.world)
|
5 |
h2aichat_com |
-1 |
» |
|
|
[OC] I built a local-first LLM canvas where deleting a wire removes that branch from context
(github.com)
|
4 |
chatchan |
8 |
» |
|
|
What's the latest and greatest AI in image editing and image2image?
|
9 |
hendrik |
10 |
» |
|
|
Field note: treat the agent's context window like a CI cost gate (budget tokens before the run, not after)
|
0 |
wartzarlab |
1 |
» |
|
|
Thoughts on Asimovian AI Beyond LLMs and Creative Machines
|
5 |
pyeri |
9 |
» |
|
|
a mockup of what "trushworthy LM search" could look like [OC, brainmade]
(files.catbox.moe)
|
16 |
maria ~ |
11 |
» |
|
|
LunarWing — self-hostable AI agent framework built in Rust, focused on privacy and real secret management
|
6 |
lunarwingorg |
7 |
» |
|
|
Thoughts on Hermes?
|
15 |
damnthefilibuster |
6 |
» |
|
|
Ideas for AI plugins welcome
(github.com)
|
0 |
nikolasdimi |
4 |
» |
|
|
llmfit - find best model that runs on your computer
(github.com)
|
3 |
vermaterc |
21 |
» |
|
|
30B-A3B GLM-4.7-Flash Released
(huggingface.co)
|
0 |
TheCornCollector |
1 |
» |
|
|
GLM-Image released: a hybrid image generation model
(huggingface.co)
|
0 |
TheCornCollector |
1 |
» |
|
|
The new Aider-CE fork of Aider AI Assistant is now official
(www.circusscientist.com)
|
0 |
tomjuggler |
1 |
» |
|
|
Change the camera position of your input image - Qwen-Image-2509-MultipleAngles
(huggingface.co)
|
0 |
vermaterc |
2 |
» |
|
|
qwen has a free video generator called wan - its really good sora alternative
(thelemmy.club)
|
0 |
Fair Fairy |
1 |
» |
|
|
Qwen offers similar UI to openai - free max, vision, image generation, has android app, seemingly uncensored
(chat.qwen.ai)
|
0 |
Fair Fairy |
1 |
» |
|
|
Which FOSAIs link to their output's online sources?
|
0 |
Prathas |
1 |
» |
|
|
Tilde AI Releases TildeOpen LLM: An Open-Source Large Language Model with Over 30 Billion Parameters and Support Most European Languages
(www.marktechpost.com)
|
0 |
cm0002 |
1 |
» |
|
|
Apertus (Switzerland’s first large-scale, open, multilingual language model)
(ethz.ch)
|
0 |
Fitik |
1 |
» |
|
|
JELSTUDIO/JEL_LLMradiotheater_Ollama: Two LLMs have a conversation using Ollama
(github.com)
|
0 |
Even_Adder |
1 |
» |
|
|
Any frontend/model that runs on a 9070XT
|
0 |
CheeseNoodle |
1 |
» |
|