Haru-4B 4B-parameter direct speech-to-speech runs offline translation on 16GB VRAM, Edge AI Lab
Mark Ku·
18MB, 70x Real-Time: The TTS Model tiny-voca Runs Without a GPU|Local AI Lab
Mark Ku·
🧪 0.8B Beats 9B: Why dale-0.8b's Offline Command-Guessing Is So Impressive | Local AI Lab
Mark Ku·
🧪 Not training, just tweaking nine weight matrices: qwen-concept-27b sparks heated debate on HN, Local AI Lab
Mark Ku·
🧪 AutoTrust-Decider-Pro-Vision-27B downloaded 158K times: deciding who AI Agents should trust | Local AI Lab
Mark Ku·
🧪 6.1 M‑download 27B model: Unsloth‑edition Qwen 3.8 lets you run multimodal fine‑tuning on a 24 GB GPU | Local AI Lab
Mark Ku·
🧪 Arete-27B 24GB 跑、0.5B TTS 4GB 跑:本週精選|地端 AI 實驗室
Mark Ku·