Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint [LAB]
Relevant to the reader's interest in quantization and efficient local inference for mid-size models. https://prismml.com/news/bonsai-2-27b (prismml.com)
Mistral and Mozilla are bringing open, private and multilingual AI to your web browser [LAB]
Significant for the local-inference landscape as it moves powerful open models toward edge/browser execution. https://mistral.ai/news/mistral-x-mozilla/ (mistral.ai)
Bend – A language that blocks AI mistakes via proof, on CPU and GPU [LAB]
A new programming language designed to use formal proofs to prevent errors across both CPU and GPU architectures. https://bend-lang.com/ (bend-lang.com)