Wirklich alles lokal: Hermes-Agent und Qwen 3.6
…Und zwar installiert ihr Ollama, das gibt es für Linux, macOS und Windows. Und wenn das installiert ist, tippt ihr einfach „Ollama“ auf der Kommandozeile ein und dann wählt ihr aus „Launch…
Search
All sources
xda-developers.com
86
github.blog
4
developer.nvidia.com
4
9to5mac.com
2
golem.de
2
huggingface.co
2
amd.com
2
blogs.nvidia.com
2
heise.de
2
appleinsider.com
1
techcrunch.com
1
notebookcheck.net
1
Tracked topic
Ollama
People also ask
Which one should you actually use now?
The real difference between Ollama's desktop app and llama.cpp's WebUI won't come through unless I use it for longer, coding-heavy workflows, but even on the surface, llama.cpp's WebUI is clearly faster and looks just as polished. Of course, where it wipes the floor with Ollama is the sheer amount of options, menus, and tweakability that it comes with. llama.cpp's WebUI lets you control sampling parameters and context settings, offloading to the GPU, and a whole host of other inference tweaks. This is a tool that exposes practically everything, so if you're the kind of person who enjoys squeez
I finally ditched Ollama after using llama.cpp's WebUI, and I'm not going back anytime soonVideos
More videosYour old GPU can still run big LLMs – you just need the right tweaks
…Not quite — the answer is Ollama. While TensorFlow Serving and CUDA Toolkit are real AI infrastructure tools, they require significantly more setup. Ollama is purpose-built for running LLMs locally and works…
I ran local LLMs on Intel's cheapest iGPU, and the results were surprisingly decent
…Related Ollama is still the easiest way to start local LLMs, but it's the worst way to keep running them Ollama is great for getting you started... just don't stick…
Google's Gemma 4 Model Can Now Be Deployed on NVIDIA's RTX GPUs, Delivering Optimized Performance for a 'Personalized' Agentic AI Environment
…Getting Started: Gemma 4 on RTX GPUs and DGX Spark NVIDIA has collaborated with Ollama and llama.cpp to provide the best local deployment experience for each of the Gemma 4 models…
Discussions and forums
ollama system ram usage extremnly high
I am having an issue with Ollama, which is connected to an app called Suggestarr (found on GitHub). When the app runs its automated recommendations, Ollama consumes an incredible amount of system RAM. This causes my fygo…
My Ollama box picks the music now: an agentic DJ running on a 9B model
I got tired of my Ollama server sitting idle between chat experiments, so I pointed it at my Navidrome library and made it run a radio station. The DJ is an agent, not a shuffler. Each turn it gets tools (search the libr…
Ollama Recommendations
I have an I5-12600 4x 4GB (16GB) 2144MHz DDR4 RTX 4060 (8GB) 10TB RAIDZ2 480GB for apps I already use the NAS for jellyfin and soon to be password manager, but I want to self host an LLM. Please give me recommendations f…
Anthropic's new MCP spec, Kimi K3 open weights on Ollama, GPT Transcribe, plus
Anthropic's new MCP spec, Kimi K3 open weights on Ollama, GPT Transcribe, plus
2
Show HN: Pair your iPhone to your own Ollama over Tailscale with a QR scan
Show HN: Pair your iPhone to your own Ollama over Tailscale with a QR scan
4
From RTX to Spark: NVIDIA Accelerates Gemma 4 for Local Agentic AI
…collaborated with Ollama and llama.cpp to provide the best local deployment experience for each of the Gemma 4 models. To use Gemma 4 locally, users can download Ollama to run Gemma…
AWS Transform now supports model-to-model migration assessment for generative AI workloads - AWS
…from OpenAI, Google Gemini, direct Anthropic SDK usage, and open-source models via LiteLLM or Ollama. It handles direct SDK integrations, framework-wrapped patterns such as LangChain and LlamaIndex, agentic architectures including…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.