This is the 4-bit MLX version of NeoHorse-1-4B for Apple Silicon. Converted from the original BF16 weights with MLX-LM, using affine quantization (group size 64). Benchmark scores below refer to the original model, not a separate evaluation of this quantized version. The model downloads automatically from Hugging Face. The original chat template is preserved. See Deployment for local checkpoints, the chat API, and tool calling. NeoHorse-1-4B Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness. / Reusable benchmark table architecture. Inline styles remain as a fallback for HF rendering. 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:
Генерация кода Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: TokenRhythm
Теги: mlx, qwen3_5, agentic, tool-use, coding, reasoning, instruction-following, 4-bit
Лайков: 3 | Загрузок: 363
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
