We present Density Field State Space Models (DF-SSM), a framework for compressing SSMs to a 1-bit scaffold with int8 low-rank correction. Applied to Mamba-2 1.3B, we achieve a 278 MB model (9.7× smaller than the 2.7 GB FP16 teacher) that runs at 21.4× faster inference on GPU (batch=1, relative to the mamba-ssm reference implementation) while maintaining downstream task performance within 2–4 percentage points of BitMamba-2, a 1.58-bit model trained from scratch on 150B tokens. The distillation itself requires only 32M tokens and 6 hours on a single A100 GPU, though it presupposes a pretrained FP16 teacher. We develop an optimized inference pipeline combining cuBLAS INT8 tensor cores for the scaffold matmul, custom CUDA kernels for stateful SSM and convolution operations, and an AVX-512 CPU backend for efficient deployment on both GPU and CPU. Beyond compression, we investigate the internal knowledge organization of the resulting model, discovering three distinct processing phases: intent classification (layers 0–3, operating in an abstract space with no vocabulary alignment), knowledge retrieval (layers 25–35, where factual associations localize to a 5-layer window), and output formatting (layers 36–47, where category structure dissolves). Through systematic analysis of 445 factual prompts across 19 categories, we find that early-layer classification is syntactic (driven by template structure) rather than semantic, and that the model exhibits well-organized knowledge representations despite weak factual recall—suggesting that representational structure may precede factual strength.
Shinde Chirag (Sat,) studied this question.