441e85161ClaimThe experimental NVFP4 checkpoint of Ricursive Intelligence's Ripple-65B Preview quantizes MLP layers while keeping attention in BF16 to target local hardware such as NVIDIA DGX SparkAgreeDisagree
441e85161ClaimOpera released example WebAI extensions demonstrating local automated tab sorting and clickbait detectionAgreeDisagree
441e85161ClaimWebAI allows local models like Google's Gemma to generate text, classify content, and identify relationships between data points within the browserAgreeDisagree
441e85161ClaimWebAI is disabled by default in Opera One, requiring users to explicitly enable the standard and grant permission for each site to access local models.AgreeDisagree
441e85161ClaimWebAI is available as an opt-in early preview on Opera One for 64-bit Windows PCs and Apple silicon Macs, with plans to support Opera GX and Opera Neon later.AgreeDisagree
441e85161ClaimOpera stated that WebAI has backing from Google and Microsoft, is model-agnostic, and supports Google's Gemma models and Apple's on-device foundation model on compatible Macs.AgreeDisagree
441e85161ClaimWebAI keeps processed information on the user's device and requires no cloud service, third-party AI subscription, or user account.AgreeDisagree
441e85161ClaimOpera began testing on-device large language models in its browser developer channel in April 2024 prior to introducing the WebAI standard.AgreeDisagree
441e85161ClaimOpera noted that local AI processing performance and speed depend on the user's hardware rather than cloud infrastructure.AgreeDisagree
441e85161ClaimWebAI allows third-party web developers to add local AI features to websites and extensions without running their own servers or paying per-request API fees.AgreeDisagree
441e85161ClaimLiquid AI released LFM3 checkpoints in GGUF, MLX, ONNX, FP8, and NVFP4 formats, supporting runtimes including llama.cpp, vLLM, SGLang, Ollama, and TransformersAgreeDisagree
441e85161ClaimLiquid AI reported that LFM3-1.7B fits into approximately 1GB of storage at 4-bit precision, enabling local deployment on laptops and mobile phonesAgreeDisagree
441e85161ClaimLiquid AI demonstrated local customization by fine-tuning LFM3-VL-2B on 3,000 wind-turbine images over several hours on an Nvidia A100 GPU, increasing classification accuracy from below 10% to 67%AgreeDisagree
441e85161ClaimDuring local testing with a 32,000-token input, Liquid AI's LFM3-1.7B recorded peak memory usage of 2.75GB on an AMD Ryzen AI Max+ 395 system, 2.25GB on an Apple M5 Max, and 1.90GB on an iPhone 17 ProAgreeDisagree
441e85161ClaimBlock designed Dessa to run locally on an Apple MacBook Pro M4 Max or higher systemAgreeDisagree
441e85161ClaimOpen-source serving software vLLM announced plans to publish demonstration code showing Reflection AI's Beam model running in the 4-bit MXFP4 format supported by AMD and Nvidia Blackwell chipsAgreeDisagree
441e85161ClaimFLUX 3 Image Klein can run locally on consumer GPUs and laptops equipped with as little as 8 GB of video memoryAgreeDisagree
441e85161ClaimBlack Forest Labs made FLUX 3 Image Klein available via its API, a web Playground, Hugging Face Spaces, and local execution frameworks including ComfyUI and DiffusersAgreeDisagree
441e85161ClaimNvidia released Nemotron 3.5 Bolt 74B-A9B 24GB, a hybrid Mixture-of-Experts model using 2-bit quantization that activates 9 billion parameters to run local agent tasks on 24GB machinesAgreeDisagree
441e85161ClaimMeta AI chief Alexandr Wang stated that the Meta-Apple collaboration allows Meta to distribute its models widely while permitting developers to run them locally without Meta receiving prompt data or user informationAgreeDisagree