{"id":"13f90495-69fa-49ff-b657-8a0fffc23ebe","slug":"hf-model-majentik-nemotron-3-nano-4b-turboquant-mlx-4bit-1vk471j-1b","name":"Nemotron-3-Nano-4B-TurboQuant-MLX-4bit","description":"Hugging Face model majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-4bit. Task: text generation. Library: mlx. 62 downloads.","capabilities":["mlx","safetensors","nemotron_h","turboquant","kv-cache-quantization","nemotron","nvidia","mamba2","hybrid","quantized","4bit","text-generation","conversational","custom_code","arxiv:2504.19874","base_model:nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","base_model:quantized:nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","license:other","4-bit"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:55.609Z"}