> Most of this README.md and the plots are generated by the Spark-X2.5-4B-IQ4XS quant.** This repository provides the imatrix quantized variants of Spark-X2.5-4B, a compact, general-purpose language model designed for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. The model uses a hybrid attention architecture, supports a native context length of up to 1M tokens, and covers more than 200 languages. The quantized variants in this repository were created following the imatrix methodology, preserving high quality while offering flexible deployment across a range of precision levels. The table below lists each quantized variant, its file size, and its recommendation status. > Note: If you are using CPU, stick with Q quants. IQ quants would be much slower on CPU. The table below reproduces the KLD benchmark results for all quantized variants. It aggregates the evaluation measurements across KLD, perplexity, and accuracy metrics for every variant. The imatrix quants were created by converting the base Spark-X2.5-4B model into a range of quantized variants, including the IQ3, Q3, IQ4, Q4, Q5, Q6, and Q8 series. Each quantized model is evaluated to…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: miifanboy
Теги: gguf, llama.cpp, ollama, lm-studio, sparkx2_5, en, zh, endpoints_compatible
Лайков: 3 | Загрузок: 871
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
