Tag: Open-Source AI
-

llama-modchip Runs a 284B DeepSeek Model on 64GB RAM, but Read the Fine Print
A new open-source build claims a 284B DeepSeek model can run on a 64GB PC with no GPU. Here is what holds up and what does not.
-

Kinference Explained: Buoyant’s Open Source Router That Aims to Speed Up vLLM on Kubernetes
Buoyant’s new open source Kinference sends each AI request to the vLLM server with the least work to do. Here’s what it claims and how to try it.
-

ERNIE 5.5 Flash Base Is Free to Download: What Baidu’s 280B Open Model Is Good For
Baidu just put a 280-billion-parameter model on Hugging Face. Here’s what you get, what’s missing, and who should bother.
-

LongCat-2.5 Preview: Meituan’s 1.6 Trillion Parameter Agent Model, and What Is Still Unproven
Meituan just put a 1.6T-parameter, 1M-token model live in preview. Here is what it claims, what it can do, and what nobody has verified yet.
-

DeepSeek V4.1 Flash Cuts Prices and Retires V4-Pro: What Changes for You
DeepSeek just replaced its flagship with a cheaper, open-weight model that sees images. Here is what V4.1 Flash costs and who should switch.
