31:33 Benchmarks2 weeks ago The Best Local Model is DeepSeek v4.1F 1017 – Frontier at Home In this Frontier AI at Home episode, sentdex evaluates DeepSeek-V4-Lite 1017, a continued-training release from October 17th, as a lo... 0 comments 1K views
14:50 Benchmarks2 weeks ago I Thought 2 TB of RAM Was Overkill… My AI Agents Disagree Alex Ziskind starts from AMD's announcement of a workstation with up to 2 TB of RAM and asks whether that much system memory matters... 0 comments 7.1K views
13:58 Reviews & Comparisons3 weeks ago 3,000 Tokens/Sec Locally: Testing the ZGX Fury Sam Witteveen takes a look at the HP ZGX Fury, HP's version of Nvidia's DGX Station, and tests how it handles local AI workloads for... 0 comments 10.6K views
18:53 News & Opinion1 month ago Flint – The First RSI Coding Model? Sam Witteveen looks at Flint, a new open-weights coding model from Recursive that aims to match mid-sized dense models at far higher... 0 comments 10.7K views
27:25 Reviews & Comparisons1 month ago Datacenter at Home – GB300 GPU – w/ Asus DGX Station (ET900N G3) Sentdex reviews ASUS's take on the Nvidia DGX Station, the ET900N G3, a workstation built around the GB300 GPU and 748 GB of coherent... 0 comments 13.5K views
15:47 Benchmarks1 month ago My Coding Agent Took 19 Seconds to Say Anything Why does a coding agent go from answering in a fraction of a second to sitting silent for 19 seconds? This video from Alex Ziskind tr... 0 comments 2.2K views
18:35 Benchmarks2 months ago I Gave Two AI Supercomputers a Real Job Alex Ziskind and guest Wendell put two high-end local AI machines to work: a system with eight RTX Pro 6000 GPUs and an Nvidia DGX St... 0 comments 4.1K views
26:34 Benchmarks2 months ago I Gave 1000 AI Agents One Computer Alex Ziskind puts the Camino Grando, a liquid-cooled workstation packing eight Nvidia RTX Pro 6000 Blackwell GPUs and 768GB of total... 0 comments 10.5K views
14:30 Benchmarks2 months ago MiniCPM5-2B: The Best Sub-Agent Model Yet? Sam Witteveen examines MiniCPM 2B (technically 2.5B), the latest small model from OpenBMB, which claims to beat 4B-class models on fu... 0 comments 4.4K views
14:42 Reviews & Comparisons3 months ago BreezeTTS2 – 100% Local Real-Time Voice Sam Witteveen takes BreezeTTS2 — a brand-new open-weight text-to-speech model from Chinese startup Breeze Blue — for a hands-on local... 0 comments 2.1K views