oQ4e (imatrix-enhanced mixed-precision 4-bit) conversion of IFM/K2-Horizon-MoVA-36B-A4B, a sparse Mixture-of-Experts model with Mixture-of-Values attention (36B total / 4B active parameters, 512K context). Upstream model: IFM/K2-Horizon-MoVA-36B-A4B by the IFM Team, released under Apache-2.0. Conversion: Quantized to MLX format using Hermes Agent with mlx-lm and oMLX. K2-Horizon is a reasoning model. Always use reasoningeffort=»high»` for best results: Independent benchmark comparison — raw scores collected via BenchLocal, report compiled by Hermes Agent. See full report. K2 wins 7/8 benchmarks. Dominates extraction, formatting, tool calling, and safety. Qwen wins only Reasoning & Maths by 2 points. Qwen is ~1.8x faster due to 3B active parameters (vs 4B) + MTP (multi-token prediction). K2 trades throughput for quality. INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED BUT SOME MAY HAVE NO CONTENT
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: mlx-community
Теги: mlx, k2_horizon, apple-silicon, oQ, conversational, custom_code, 4-bit
Лайков: 3 | Загрузок: 499
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
