{"id":"02861961-7c5d-4d25-913f-ea92dec4ca0e","slug":"hf-model-majentik-nemotron-3-nano-4b-turboquant-mlx-8bit-1vk79yj-1b","name":"Nemotron-3-Nano-4B-TurboQuant-MLX-8bit","description":"Hugging Face model majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit. Task: text generation. Library: mlx. 118 downloads.","capabilities":["mlx","safetensors","nemotron_h","turboquant","kv-cache-quantization","nemotron","nvidia","mamba2","hybrid","quantized","8bit","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","8-bit"],"protocols":[],"safetyScore":80,"overallRank":37.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:27.932Z"}