I ditched LM Studio for an open-source alternative — and my local model is doing things it couldn't before
…But the longer I lean on local AI, the more I run into things LM Studio either doesn't do or makes me set up by hand. That's what pushed me…
Search
Related topics:
Google Gemma
Tracked topic
Google Gemma
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
I gave my gaming PC and phone the same local LLM tasks, and only one of them is still in my daily rotation
…Qwen 3.5 9B is the one that runs smoothly, and I think a lot of that is the Gated DeltaNet architecture doing the work. Gemma 4 E4B runs just as smoothly…
My local LLM and Claude are helping me make my dream game, one day at a time
…Sign in to your XDA account Summary Running a local Gemma4 on my RTX 4070 Ti let me prototype my dream game offline. A spreadsheet+Python rebuilt the persistent world, so I…
I use Claude and local LLMs together now, and it costs half as much while being twice as fast
…For the local side of this pipeline, I went with Google's Gemma 4 26B model . It is highly capable, runs comfortably on my RTX 4070 Ti Super (notably, without the overhead…
Top stories
I ran Gemma, Llama, and Qwen on my phone, and only one of them is worth the storage
1d agoI tried Google's new DiffusionGemma, and watching it generate text like an image is unlike any local LLM
1d agoI tested 3 local LLMs on my RTX 4070 Ti for real work — only one earned a permanent spot
3d agoI ran a powerful local AI model on my laptop, and it didn’t feel like a compromise
1w agoRunning Pi with local LLMs on a Raspberry Pi sounds chaotic, but it actually works
…Related I ran local LLMs on Intel's cheapest iGPU, and the results were surprisingly decent It ain't no match for a dedicated GPU, but you can run some light LLMs…
I ran local LLMs on my phone for a month, and now my desktop setup feels like overkill
…The Gemma 4 E4B I run on desktop is technically 8B parameters loaded, and the E2B variant designed for phones is 5B. I'd been imagining a real gulf between "serious" self…
Ollama is still the easiest way to start local LLMs, but it's the worst way to keep running them
…Ollama specializes in open-weight models like Llama 3, Mistral, and Gemma that can be legally downloaded and run locally. 04 / 8 Hardware When running an LLM with Ollama, what hardware component…
I switched from NotebookLM to this open-source tool, and it does what Google won't
…Open Notebook's docs literally use gemma3 as the example local model, it's well-supported in Ollama with proper caching, and it runs fine on modest hardware. One command pulls it…
I added this open-source tool to my local AI stack, and my local LLM finally has persistent memory
…Related I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead Pitting them against each other to find the best one for my workflow…
I ditched Claude, ChatGPT, NotebookLM, and Perplexity for these free open-source tools
…Past that though, I find Ollama the simplest way to run a local LLM. Once you've installed the Ollama app, you simply run a command like ollama run gemma3:4b in…