TensorRT Edge-LLM Completes MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor
NVIDIA says TensorRT Edge-LLM ran Qwen3.6-27B 6.4x faster on Jetson AGX Thor, highlighting cache and quantization gains for edge agents.
Edge AI
Latest News and Analysis in Edge AI
Edge AI
NVIDIA Details How Jetson Can Run New Reasoning Models at the Edge
NVIDIA’s Jetson deployment guide shows how quantization and speculative decoding can bring compact reasoning models to local edge AI workloads.
StartLux’s 27B Local Model Reportedly Beats DeepSeek V4 Flash in China Benchmark
StartLux’s 27B local model reportedly outscored DeepSeek V4 Flash in a China benchmark, raising questions about edge AI performance and proof.
NVIDIA Details Agent-Assisted Workflow for Building Holoscan Medical AI Applications
NVIDIA details an agent-assisted Holoscan workflow using CLI, skills, and HoloHub to build and benchmark real-time medical AI applications.
The Register Explains Why Edge AI Is Moving Closer To Data
The Register explains the enterprise shift toward running AI applications closer to where data is generated and consumed.
China’s AI Hardware Push Moves Models From Cloud To Devices
Chinese companies are embedding AI into cars, robots, and industrial products as the technology shifts toward edge devices.
PrismML Debuts Energy-Efficient 1-Bit LLM to Free AI From the Cloud
Caltech-backed PrismML released Bonasi, a 1-bit LLM that is 14x smaller and 5x more energy efficient than comparable 8B models, aiming to run AI without cloud dependency.
Arm CEO Highlights Edge AI as Next Frontier for Distributed Intelligence
Arm CEO Rene Haas at Davos emphasizes shift from centralized data centers to distributed edge AI, addressing energy and memory bottlenecks.
Ads