New, promising MoE model "Hunyuan" by Tencent

https://lemmy.ml/post/32831762

Are you using any MCP servers? If so, what?

https://lemmy.ca/post/46905423

Homelab upgrade WIP

https://lemmy.world/post/32071278

Do you quantize models yourself?

https://lemmy.ml/post/32231409

Any recomendations for an text editor with good AI integration (not code editor)

https://lemmy.world/post/31850136

Local Voiceover/Audiobook generation

https://infosec.pub/post/29845011

Mistral releases Magistral, official mistral small reasoning model

https://lemmy.world/post/31175078

Current best local models for tool use?

https://lemm.ee/post/66465951

I'm excited for dots.llm (142BA14B)!

https://sh.itjust.works/post/39817345

What to Integrate My AI With

https://sh.itjust.works/post/39767232

Updated guidelines for c/LocaLLama (new rules)

https://lemmy.world/post/31038465

AMD’s Untether AI Deal - Bad Signs for GPU-Driven AI training

https://aussie.zone/post/21339438

My AI Skeptic Friends Are All Nuts

https://aussie.zone/post/21200045

Despite record gaming revenues, Nvidia reportedly plans to cut RTX 50 series production to allocate it to new AI hardware

https://lemmy.ml/post/30982488

Noob experience using local LLM as a D&D style DM.

https://sh.itjust.works/post/39139782

Don't overlook llama.cpp's rpc-server feature.

https://sh.itjust.works/post/39137051

LLMs and their efficiency, can they really replace humans?

https://lemm.ee/post/65523085

Deepseek just released r1 distilled qwen3 models, boast improved performance over original models

https://lemmy.world/post/30442991

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally on your phone. APK

https://feddit.it/post/18063918