Spark-X2.5-4B at 3.41 GiB — the size-first bundle. Fastest of the pair, and the one to run if you want headroom. A JANG bundle of XHToken/Spark-X2.5-4B — a 4.112B dense reasoning + tool-use model — quantized for Apple Silicon / MLX. Attention and the tied embedding stay at 8-bit; the MLP carries the 6-bit budget. Every group scale is bfloat16, and the per-head attention gate and all norms are kept in full precision. Sibling bundle: JANGQ-AI/Spark-X2.5-4B-JANG_8M — higher fidelity at 4.07 GiB. 15,839 teacher-forced positions on held-out prompts, versus the bf16 source. Calibration and evaluation prompts come from disjoint corpora, asserted at eval time. Decode measured as the median of 4 probes at a fixed condition (512-token prompt, 128 generated), first probe discarded, on an M5 Max. Prefill 5046 tok/s. There is no stock-MLX comparison row, and that is not an omission. mlx-lm has no spark25` architecture — not in any release, not on main — so no stock MLX quantization of this model can be loaded or scored. The MLX runtime ships with these bundles. 1,759,492 calibration tokens spanning code, agentic/tool-call transcripts, academic multiple-choice, general chat, Chinese,…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: OsaurusAI
Теги: mlx, spark2_5, jang, quantized, apple-silicon, reasoning, agent, tool-use
Лайков: 3 | Загрузок: 354
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
