MLX

2 posts tagged

Why Qwen3.5 Falls Into Infinite Thinking — and How to Fix It

April 2, 2026·12 min read

MLX Rust LLM Qwen3.5 Reasoning

Unsloth MLX: Bring Dynamic 2.0 Per-Tensor Quantization to Apple Silicon

March 24, 2026·7 min read

MLX Rust Quantization LLM Unsloth