giostrives/TensorFold
Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint
Striving to use AI for learning and making a positive change.
Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint
Qwen3.8-Flash-Next (125B MoE) on a 8GB+ NVIDIA GPU: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Claude Code skill: turn a messy phone recording into an edited vertical reel (best takes, captions, animated overlays, memes)
Plugin to use LLMs to help in card review