This is an MTPLX pair bundle for Gemma 4 31B speculative decoding on Apple Silicon. It is not a single vanilla Transformers model directory. The repository contains two MLX-format artifacts: — target/ — Gemma 4 31B IT target, MLX Q8 affine group-size 64 — assistant/ — official Gemma 4 31B assistant drafter, MLX Q8 affine group-size 64 Use this pair when target precision and high acceptance are the priority. — Target source: google/gemma-4-31B-it — Target revision: 145dc2508c480a64b47242f160d286cff94a2343 — Assistant source: google/gemma-4-31B-it-assistant — Assistant revision: cffbbd2cea41ea56a0fa5b0487e0d445121fd204 After downloading this repository, point MTPLX at the two subdirectories: The Gemma 4 assistant is a separate drafter model. MTPLX uses exact speculative sampling with target verification and residual correction. Prompt: single-file HTML5 Canvas Flappy Bird game, capped at 1000 generated tokens. This release is optimized for target precision and high acceptance. It is not the fastest absolute-TPS pair; for speed, use Youssofal/Gemma4-MTPLX-Optimized-Speed. Gemma 4 is released by Google under the Gemma 4 license terms linked above.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Youssofal
Теги: mlx, gemma4, mtplx, speculative-decoding, apple-silicon
Лайков: 4 | Загрузок: 0
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
