GGUF, Safetensors, and MLX quantized formats of tencent/Hy-Memory-30B-A3B for local memory operations and agent execution. Tencent’s Hy-Memory-30B-A3B is a specialized Mixture-of-Experts (MoE) model (30B total parameters, 3B active per token) trained specifically as a high-performance memory writer and agent-memory operator. It excels at session summarization, context compaction, entity memory extraction, and agent memory management. Q4KM is recommended for the best balance of size and quality for GGUF. NVFP4 and FP8 offer high performance on supported NVIDIA GPUs, while MLX formats are optimized for Apple Silicon. Run multi-turn interactive conversation directly in your terminal: Start llama-server to serve OpenAI-compatible /v1/chat/completions endpoints: For Apple Silicon Macs, load MLX quantized weights (4-bit, 6-bit, or 8-bit): Load the quantized weights directly via safetensors for TensorCore-accelerated pipelines (such as comfy-kitchen, vLLM, or custom inference): — Source model: tencent/Hy-Memory-30B-A3B — Architecture: HYV3ForCausalLM (MoE: 128 experts, 8 active per token, 30B
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: abenzerps
Теги: gguf, mlx, fp8, nvfp4, tencent, hunyuan, memory, agent-memory
Лайков: 3 | Загрузок: 1,145
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
