EmbeddingGemma 2: one space for text, images, video and audio, on consumer hardware
Model releasesRelated articles
Yzma: embeddings up to 2.6x faster than Ollama, the comparison
Yzma calls llama.cpp in the same process: no server, no round trip. It is 2.6x faster than Ollama on embeddings — with the numbers, the math and the setup.
Local Images: ComfyUI 0.40 and comfy_attention — new for all models
ComfyUI 0.40 extends the comfy_attention attention engine to all models, turns on the local asset API, and standardizes 3D output. Plus the VRAM table that tells you what runs on your hardware.
Aleph Alpha's Kolibri: the 78B MoE that runs (almost) locally
Kolibri ships 78B open-weight parameters in an FP8 format built for local hardware: 3.46B active per token, Apache 2.0, context up to 1M. We test it: real VRAM costs and current limits.
Get the next local-AI briefing
Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.
After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

