This is a persisted 4-bit MXFP4 MLX checkpoint for sapientinc/HRM-Text-1B. It is intended for use with HRM-mlx on Apple Silicon. This is not a new finetune. It is a quantized inference checkpoint derived from the public HRM-Text-1B weights. — model.safetensors: MLX-format 4-bit MXFP4 weights — config.json: HRM-Text config with MLX metadata — quantization.json: quantization metadata — tokenizer.json, tokenizerconfig.json`: tokenizer files copied from the base model On a MacBook Pro M4 Max, 32-core GPU, this checkpoint reaches about 56 decode tokens/sec with HRM-mlx’s fast path: Benchmark shape: 512 prompt tokens, 128 generated tokens. Absolute numbers vary by chip and system load. This checkpoint has not been evaluated with a formal benchmark suite. In a small qualitative check, 4-bit MXFP4 matched BF16 on simple math and short reasoning prompts, including the derivative of (x^2) / ln(x). HRM-Text-1B is a base reasoning model, not a polished chat assistant. It can produce incomplete or unstable answers on some prompts, especially when the prompt is underspecified or contradictory.
Модальности:
Генерация текста
Области применения:
Логика и рассуждение
Задача: Генерация текста
Автор: Aryagm
Теги: mlx, hrm_text, apple-silicon, quantized, mxfp4, hrm, reasoning, custom_code
Лайков: 3 | Загрузок: 38
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
