Why Did Qwen Become a Staple of Local AI? Part 1: From the First Qwen to Qwen2.5, a History and Popularity Check
If you try to run AI locally, the name "Qwen" ...
Can the AI That Writes No Text, Jev, Run on an RTX 3090? Measuring One Decision on a Local Version
16 October 2026 Some AI models do not write t ...
What Is Strata? How a 12GB GPU Runs a 125B Model: Mechanism, Speed, and Supported Setups
A model too big to fit in GPU memory (VRAM) r ...
Is Waiting for a Long Text Proportional to Its Length? I Measured Time to First Token in Seven Steps of Input
Input length stepped in seven stages up to ab ...
Models Installed With Ollama Won’t Load in llama.cpp? The Seven That Failed, and Re-measuring From Hugging Face
Seven of 22 Ollama blobs failed to load in ll ...
Can Moving 3D Gaussian Splatting Be Streamed by Sending Only What Changes? Formats and Real Uses of 4DGS Delivery
Does sending one reference frame plus only th ...
What Runs on a Phone or in an App? 23 Small Generative AI Models Compared on Smartness, Speed and Size
MiniCPM5-2B and 22 other small models (0.6B-7 ...
I Want to Look at 3DGS: Free Viewers on the Web, Phone, Steam and Quest, Compared
Free 3D Gaussian Splatting viewers for browse ...
Slower Despite the Name “Lightning”? I Measured the New and Old Nemotron Side by Side
I measured Nemotron-3.5-Lightning-30B-A3B aga ...
DGX Spark Gets a 64GB Version and the 128GB Gets Pricier: What Fits in Half the Memory, Checked Against EVO-X2 Measurements
NVIDIA announced a 64GB DGX Spark at $4,999 a ...









