Search results for "Qwen3.6"

Technology 17 Sep 2026

NVIDIA's TensorRT Edge-LLM Runs Qwen3.6-27B 6.4x Faster in MLPerf Edge Agentic

NVIDIA says TensorRT Edge-LLM ran Qwen3.6-27B through the MLPerf Edge Agentic workload in 24 minutes 36 seconds on one Jetson AGX Thor. The 6.4x gap over llama.cpp puts long-context agent inference on edge.

Technology 16 Sep 2026

NVIDIA Vera Rubin NVL72 debuts in MLPerf Inference v6.1 with up to 3.7x throughput over GB300 NVL72

NVIDIA submitted its first MLPerf Inference v6.1 preview results for Vera Rubin NVL72, showing up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL. The numbers signal a leap for rack-scale inference on MoE models.

Technology 10 Aug 2026

Meta Releases Muse Glimmer: 30B Open Agentic Model Runs Locally on Consumer GPUs

Meta's Superintelligence Labs has released Muse Glimmer, a 30-billion-parameter open-weight model built specifically for always-on local agent workflows. Local agentic models change the economics of AI deployment.