ich hab den lokalen llm-kram umgestellt von lm-studio + goose auf ramalama + opencode
so kann ich in zukunft auf allen systemen die gleichen tools nutzen.
opencode fühlt sich im terminal auch viel mehr nach zu hause an auf linux. goose hat ohne große konfiguration immer seltsame aktionen ausgeführt.
opencode verhält sich erwartungsgemäß. sprich man fragt "zeige alle dateien an" und es folgt ein ls -l usw.
https://ramalama.ai/
https://opencode.ai/docs/de
#ramalama #opencode #localai
Local AI is now part of your security surface — inference logs, model directories, embedded weights are all endpoints to track.
The upside? If you own the hardware, you own the audit trail. Cloud inference gives you zero visibility into what model versions ran your queries or when.
On-prem doesn't just save money — it's the only way to actually govern your AI stack.
My biggest headache building a search engine for Salvadoran documents? Half the PDFs are just scans. No text, nothing to search!
▶ Full write-up: https://jocheojeda.com/2026/06/01/ocr-image-only-pdfs-with-a-local-vision-model-lm-studio/
Local AI is a stack: model weights, a runner, an interface, and a boundary for what stays on your machine. Start with one real task before you buy hardware or chase benchmarks.
#LocalAI #OpenSourceAI #AIInfrastructure #AIWorkflow #KyaniteLabs
Google wants your next AI agent running locally on a 16GB laptop
https://fed.brid.gy/r/https://nerds.xyz/2026/06/google-gemma-4-12b-local-ai/
It now includes endpoint storage, removable media, local model directories, inference runtimes, embeddings, plug-ins, automation scripts, and the increasingly blurry line between personal productivity and enterprise workflow.
Read more 👉 https://lttr.ai/AryKC
After a month of daily use, my favorite local AI coding model is still **Qwen3.6-27B**.
Setup:
🐧 openSUSE Tumbleweed
🖥️ Ryzen 9 9950X3D
🎮 RX 9070 XT 16GB
💾 64GB RAM
🤖 LM Studio + Claude Code CLI
🛠️ skills.sh / skill.fish
For Linux, Python, Bash, JavaScript, Vue.js, and Nuxt.js work, it has given me the best overall experience of the local models I've tested.
#AI #LocalAI #Qwen #LMStudio #ClaudeCode #Linux #openSUSE #Python #VueJS #NuxtJS
New week, beautiful new slides: Run LLMs Locally
Now with Mellum2 from JetBrains!
A very fast coding model, requires only 10 GB RAM.
I also added LFM 2.5 from LiquidAI, updated translations with HY-MT2 from Tencent, added examples for wllama using re-ranking and structured output
and added thinking_budget_tokens to the curl examples.
https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf
#ai #llm #llamacpp #wllama #stablediffusion #qwen3 #glm #localai #gemma4 #webgpu #opencode #mtp #webassembly #jetbrains #mellum2
wiulinu
Clawbox
Joche Ojeda
Kyanite Labs
NERDS.xyz – Real Tech News for Real Nerds [Unofficial]
LBHuston
The Linux Lighthouse
Thomas