Ollama Search Integration which is available at https://github.com/nik549/ollama-search turns my sight to Searxng I already saw it in some solutions, but with that project I can see it’s potential in my projects….
Zyphra/Zonos
Zonos-v0.1 is open-weight text-to-speech model, is trending on HF. It was trained on over 200k hours of diverse multilingual speech, resulting in expressiveness and quality comparable to — or even surpassing —…
Lumina Image 2.0
Lumina 2.0 is a solid base model that fulfills our expectations for SD3/3.5. It’s truly open-source with an Apache 2.0 license, which is a significant advantage. In terms of comparison with Flux,…
Repo Prompt + Deepseek R1 API
Repo prompt has now native support for Deepseek API, and few more improvements. But also what is more important for me it works very well with Mistral 24B XML plans. Maybe not…
DeepSeek R1 – model quantization for customer grade cards
This model has shaken the NASDAQ, so it is not a big surprise that people started to adapt it further. The requirements are very high for home / hobby usage, but already…
DeepSeek R1
DeepSeek R1 is available for regular users, in examples it beats o1 reasoning, there are also smaller models available 1.5B so quite a good potential to be tested. Exolabs of course tested…
Weebo
Weebo is a simple and pleasant solution that allows you to interact with AI locally. It utilizes Whisper MLX, Ollama (llama3.2), and Kokoro-82M. For my machine, I switched from real-time listening to…
Kokoro TTS Model, LLM Apps Curated List
Kokoro Kokoro is an 82 million parameter text-to-speech (TTS) model that has made significant advancements in the field. Here are some key highlights: * Released under Apache 2.0 license, making it freely…
The Agent Company
Recently, a few tweets appeared about the next level of job replacement – it’s just a simulation, but it’s still showing the progress that some of us are not aware of. One…