studioburnside/mlx-local-inference-benchmarks download history
studioburnside/mlx-local-inference-benchmarks is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 83 times (7 in the last 7 days), and 801 times in total. It ranks #174,348 among datasets by monthly downloads.
MLX local-inference benchmarks — Qwen3.6 & Laguna-S/XS families Raw results, harnesses and methodology for an 8-axis benchmark of four MLX checkpoints on a 128 GB M5 Max. Everything a person would need to check my numbers or disagree with them. Companion model repos: Tess-4-27B-MLX-Q
Open studioburnside/mlx-local-inference-benchmarks on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.