maruhana·20h agoImage Translation with a Local LLM: 30 Seconds on My Laptop’s CPU, 0.7 Seconds on a GPUTranslateGemma 4B in Ollama, fed one new 1920x1080 image at a time: 29–34 s on a laptop CPU, about 0.7 s on an RTX Spark GPU. The image…
maruhana·3d agoWhisper turbo vs. medium on Arm and CUDA: The Faster Model Still Flipped Between CPU and GPUwhisper.cpp v1.9.5, one recording, four builds (x86 CPU, Intel iGPU, Arm CPU, RTX Spark CUDA): medium was faster on both CPUs, turbo was…A response icon1A response icon1
maruhana·6d agoI Cut Dedicated GPU Memory to 4GB, and a Local LLM Still Ran at 90% SpeedOn a Surface Laptop Ultra (RTX Spark, unified memory), I measured local LLM speed and Windows’ free memory with the GPU’s dedicated memory…
maruhana·Nov 14A 120B Model Ran About 4× Faster Than a 27B One: 8 Local LLMs on a Surface Laptop UltraSame llama.cpp build, same commands, one Surface Laptop Ultra (Windows on Arm, RTX Spark): generation speed lined up by active parameters…
maruhana·Nov 12Moving ComfyUI from Intel Arc to Arm WSL2: The Same requirements.txtMeasured on a Surface Laptop Ultra (Windows on Arm, RTX Spark): PyTorch 2.14.1+cu132 just worked on the GPU; torchaudio was the only piece…
maruhana·Nov 9Ollama vs. llama.cpp on the Same GGUF: The 15% Speed Gap Was the Defaults, Not the EngineMeasured on a Surface Laptop Ultra (Windows on Arm, RTX Spark): align the draft and sampling settings, and the gap mostly disappears.
maruhana·Nov 8Rokid Glasses Can Record 4 Microphone Channels, But Only If You Ask for Exactly 4Measured on a real RV101: which channel carries your voice, which carry the room, and the claims I had to take back.