Lemonade post-trained Hy3, a 295B model, to generate Roblox UI in its agentic Roblox Studio harness, targeting parity with Grok 4.5 at lower cost for its hundreds of thousands of users. The team built…
Developer Rebreda's open-source Listenr project reached 27 GitHub stars as of October 2026, up from 1 star at its first commit in October 2025, according to a first-person account of the project's gro…
AMD detailed a local quantization workflow using AMD Quark 0.12.post1 that compressed the Qwen3.6-35B-A3B Mixture-of-Experts model from BF16 to W4A16 on a single Strix Halo system, cutting model weigh…
F-Secure and AMD Silo AI demonstrated a joint approach that routes each piece of data to on-device or cloud AI models based on sensitivity, cost, model capability and performance, with F-Secure planni…
A new guide from developer Adam C. shows how to run a local AI coding assistant in Visual Studio Code using IBM's Granite 4 tiny model and the Lemonade server, eliminating the need for a GitHub Copilo…
Lemonade, an open-source local AI server written in C++, shipped an update in August 2026, according to its GitHub repository, which has 5.3k stars. The project, optimized by AMD engineers for Ryzen A…
AMD has released Lemonade, a free, open-source AI inference server that lets users run generative AI models locally on their own computers, showcasing the AI capabilities of AMD's latest Ryzen CPUs, R…
A developer ran GPT-2 XL (2019) and Qwen3-0.6B (2025) locally on the same laptop through AMD's Lemonade server, finding a 11x speed gap after correcting measurement errors. The project, called Second …
Cisco and AMD are partnering to build an enterprise-ready architecture for local AI on AMD Ryzen AI Halo hardware, addressing network, tokenomics, agent behavior, and security challenges. The solution…
AMD-backed open-source project Lemonade released version 11.5 of its local AI server, featuring the completed Lemonade Router for automatically routing queries to relevant models based on rule, classi…
AMD announced that the developers behind FastFlowLM, an open-source inference software for AMD Ryzen AI NPUs, have joined the company to advance client and workstation AI software. The FastFlowLM team…
AMD released GAIA 0.22, its latest local AI app update, with enhanced email capabilities including tracking pending emails, drafting replies that mimic the user's writing style, and scheduling email p…
AMD released Lemonade 11.0, the latest version of its open-source local AI server for AMD Ryzen CPUs, Radeon GPUs, and Ryzen AI NPUs on Windows and Linux, adding text-to-speech via an OpenMOSS backend…
AMD's Lemonade runtime and AI Playbooks enable local AI coding agents on Windows, using an OpenAI-compatible API, model router, per-device backends, and a policy engine to decide where each request ru…
Geology's June 2026 insurance study found that incumbent insurers capture 78-82% of mentions on ChatGPT, Perplexity, and Gemini, and 66% on Google AI Overviews. The company developed a measurement fra…
Artemis Security, an AI-native threat detection platform, achieved a 69x speedup in detection queries by coalescing hundreds of rule scans into single queries using ClickHouse Cloud. The startup also …
AMD Radeon GPUs, both integrated and discrete, now support running large language models locally through open-source tools like Lemonade, LM Studio, Ollama, and llama.cpp. A new guide provides step-by…
Former Israeli prime minister Naftali Bennett announced the formation of a national AI advisory committee to develop long-term policy recommendations in innovation, education, regulation, and security…
AMD-backed Lemonade AI server released v10.8 with Model Context Protocol (MCP) server integration, enabling MCP-compatible clients like GitHub Copilot and Claude Desktop to use local AI models as tool…
Canonical and AMD have integrated the AMD ROCm AI/ML and HPC software stack directly into the Ubuntu 26.04 LTS archive, enabling users to install the libraries with a single `sudo apt install rocm` co…