The Luce-Org organization achieved 207 tokens per second with the Qwen3.5-27B model running on an RTX 3090 GPU. This performance benchmark demonstrates the hardware's capabilities with the large language model.
The article provides a command-line recipe for transcribing audio files on macOS using the Gemma 4 E2B model with MLX and mlx-vlm. It demonstrates the transcription of a 14-second WAV file, noting minor misinterpretations in the output.
When working with 24-bit-per-pixel formats on video cards with bank-switched memory, code had to use aligned memory accesses despite the pixels themselves not being aligned. This requirement was necessary due to the hardware constraints of bank-switched video memory architectures.