> Built with mlx-optiq, the MLX-native toolkit to > quantize, fine-tune, and serve LLMs locally on Apple Silicon (no PyTorch, no > cloud). Try the Lab · All OptiQ > quants · Docs An OptiQ mixed-precision MLX quant of LLaDA2.2-flash, a ~100B diffusion language model with a 256-routed-expert sparse MoE. This is an extreme 2-bit build. — Mixed 2/4-bit static build — per-layer bit-widths assigned to a 2.5 target bits-per-weight. — 192 GB bf16 to 36 GB on disk (5.3x). Needs optiq >= 0.4.4, which ships the vendored llada2moe decoder (the 256-expert diffusion MoE) and the block-diffusion decode loop. Stock mlx-lm has no llada2moe arch and cannot load or generate from this repo. LLaDA2 is a masked-diffusion model, not autoregressive — it denoises a canvas block by block. optiq serve detects the arch and routes it through OptiQ’s vendored decoder and the block-diffusion decode loop automatically: Then call the OpenAI-compatible endpoint at http://localhost:8000/v1, or use it from the OptiQ Lab and optiq code.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: mlx-community
Теги: mlx, llada2_moe, optiq, diffusion, conversational, custom_code, en, 4-bit
Лайков: 4 | Загрузок: 311
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
