An AXQuant (AXQ) mixed-precision MLX checkpoint for Apple Silicon, converted directly from the BF16 source model. The language path is quantized while the multi-token-prediction (MTP) head and vision tower are preserved at BF16 in the checkpoint (or a bound sidecar when present). > Checkpoint Tier 1 certified on df-macbookpro-m3 (2026-08-14) at Hub commit > 32f448461caf — measured size against a matched uniform baseline, quality retention, > and conversion integrity. Current main preserves that revision’s exact Safetensors > payloads while allowing metadata-only compatibility fixes. Tier 1 is a checkpoint claim, > not a general speed claim: MTP acceleration is certified for the certificate’s > authorizing profiles only; outside that scope there is no speedup claim. > See the checkpoint Tier 1 certificate and Tier 2 MTP acceleration certificate for the bound evidence and thresholds. This repository contains MLX Safetensors. It does not contain PyTorch or GGUF weights. AXQ names describe a storage-budget product class, not one uniform precision applied to every tensor. Protected tensors remain at higher precision, so the exact measured BPW is authoritative. In particular, a…
Модальности:
Генерация текста Компьютерное зрение
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: AutomatosX
Теги: mlx, qwen3_5, apple-silicon, quantized, mixed-precision, axquant, axq, development
Лайков: 4 | Загрузок: 3,554
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
