MLX 4-bit affine quantization of poolside/Laguna-S-2.1, packaged for Apple Silicon experiments and local OpenAI-compatible serving. Laguna S 2.1 is Poolside’s 118B-total / ~8B-active Mixture-of-Experts model for agentic coding and long-horizon software work. This repo keeps the same tokenizer, chat template, and Laguna custom code files, with the weights converted to MLX 4-bit group quantization. > This is a community conversion. Model architecture, license, intended use, and safety guidance belong to the original Poolside release. — Sparse-MoE design: 256 routed experts plus one shared expert, with top-10 routing. — 48-layer Laguna S architecture with a 1:3 full-attention to sliding-window layout. — 512-token sliding window layers help keep long-context decode memory bounded. — Native reasoning controls through enablethinking` in the chat template. — Built for coding, tools, and long-horizon agent workflows rather than short chat only. These are Poolside’s reported base-model results for Laguna S 2.1, included here for context. They are not fresh benchmark runs of this MLX quantization. See the original model card for the full table, comparison models, methodology notes, and…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат
Задача: Генерация текста
Автор: Vontra
Теги: mlx, laguna, mlx-lm, mixture-of-experts, quantized, 4-bit, apple-silicon, code
Лайков: 4 | Загрузок: 372
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
