把Mamba-2压缩到1比特权重不用花大钱从头训练，用预训练模型加少量微调就行，效果只差0.3%。
Mamba-2 1.3B参数模型通过分组量化感知训练（QAT）从FP16教师蒸馏，仅消耗4 GPU小时（单H100）和102M tokens，将内存从2,687 MB压缩至744 MB（3.61倍）。零样本七任务平均准确率达48.1%，接近Bi-Mamba的48.4%（±0.9pp置信区间）。该方法无需从头训练150B tokens，使用预训练检查点即可。研究还发现零比例坍缩现象，即可学习量化尺度导致的不稳定性，这在从头训练中不会出现。后处理校正策略对SSM无效，因循环结构导致误差累积。
Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models
State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment. Prior ternary SSM work (Slender-Mamba) trains from scratch on 150B tokens; we show a pretrained checkpoint suffices, reducing the marginal token budget by 1,000x. Using grouped quantization-aware training (QAT) with knowledge distillation from a frozen FP16 teacher, we compress Mamba-2 1.3B to 3.61x (2,687 to 744 MB) and achieve 48.1% zero-shot accuracy (7-task average) in just 102M tokens (4 GPU-hours, single H100) -- approaching Bi-Mamba's 48.4% (within +/-0.9pp CI). This QAT-from-pretrained setting reveals zero-ratio collapse, a novel instability caused by learnable quantization scales that does not arise in from-scratch training. We further show that post-hoc correction strategies effective for Transformers fail for SSMs due to error accumulation through the recurrence. These results demonstrate that ternary SSMs do not require expensive from-scratch training: QAT from pretrained checkpoints with KD is a data-efficient alternative.