Use it from OpenCode / Claude Code / Codex: rapid-mlx agents —setup · Agent setup An official Rapid-MLX, self-contained MLX package of Qwen3.8-27B. It includes both the 4-bit target weights and the matching native Multi-Token Prediction (MTP) drafter in model-mtp.safetensors. Users download one repository; the target and acceleration weights stay paired. The MTP weights were derived from the same upstream Qwen checkpoint as the target. Upstream model license and limitations continue to apply. Use a Rapid-MLX release that supports Qwen3.8 native MTP. Rapid can load the target and use the colocated model-mtp.safetensors as its MTP sidecar. MTP is speculative decoding: accepted output remains identical to greedy autoregressive decoding. Runtime should fall back to autoregressive decoding when MTP is unavailable or is not beneficial on the current Mac. On an Apple-silicon Studio test system, a paired greedy smoke test produced the same emitted-token hash with and without MTP. One measured prompt ran at 39.66 tok/s autoregressive and 46.73 tok/s with Rapid MTP (1.18x). Performance varies by prompt and hardware; this is a compatibility result, not a universal speed claim. -…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: rapid-mlx
Теги: mlx, qwen3_5, rapid-mlx, qwen3.8, qwen3.8-27b, 4-bit, mtp, speculative-decoding
Лайков: 3 | Загрузок: 1,374
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
