Compact models like LFM3, on-device browser agents and consumer GPU optimizations move AI workloads to edge devices; cloud cost pressure and agentic tooling accelerate the local shift.
SenseNova brings to Hugging Face a multimodal LLM with reused decoder blocks and hybrid attention. With 24 layers run twice and 56 executions from 32 distinct layers, it targets agentic workloads and documents up to 256K tokens. The approach reduces ...
The first Loom SDK v0.1 from AMD marks the start of the Hyperloom roadmap announced at Advancing AI, aiming to optimize agentic workloads across CPUs, GPUs and NPUs. For local deployment, the signal is twofold: AMD wants to unify the ROCm ecosystem, ...
Liquid AI has introduced LFM3, a family of compact models from 1.7–2.2 billion parameters with a tri-hybrid architecture and llama.cpp support. The decision models skip token generation and return calibrated answers in a single forward pass. For on-p...
A study across seven models and three benchmarks shows that LLM agent skills are not universal: what improves a strong model can degrade a weak one. In 86% of weak-model failures, the violated requirement was already stated in the skill. Adaptation g...
Demand for local AI infrastructure is growing as cloud costs weigh on budgets. Supply for Asus RTX Spark is tightening, signaling a market shifting resources toward on-premises computing. The trend highlights pressure on hardware, lead times, and dep...
Liquid AI has released a family of models ranging from 1.7 to 2.2 billion parameters, designed to run on phones, laptops, and edge devices. Beyond text, there are multimodal versions and decision models that return answers in a single pass. The commo...
A modification to Nvidia RTX 20, 30 and 40 series cards removes a limit that halves performance in AI workloads. The case touches the core of local inference and TCO for those choosing consumer hardware.
The Swedish startup Strawberry exits beta with an enterprise browser that embeds AI assistants. Agents run on the user's device, not on cloud servers, which can address data sovereignty demands. The company has raised $6 million and plans to scale ac...
An independent project has shared an early 4-billion-parameter model for coding and 3D scene generation, fine-tuned from Qwen3.5-4B. GGUF checkpoints Q4_K_M and Q8_0 are available on Hugging Face while training continues. The author plans to update t...
