super-weights-kquant

mixedPythonInference & servingJuly 11, 2026

the question

Is a model's 'super weight' criticality universal, and does protecting it help K-quantization?

what came out

Capacity-gated: Qwen2.5-0.5B has one isolated super weight (6.4x PPL), the 1.5B has none. It hijacks a Q2_K block scale 131-204x, but production stores down_proj as Q3_K, so protecting it recovers only ~5% of the 2-bit loss. Bounds Yu et al. at sub-1B; exact 2-byte GGUF oracle.

method & receipts

Result: mixed
Pre-registered — the prediction was written down and committed before the run.
Reproducible — one script re-runs the whole thing from scratch.

→ read the code and re-run it

github.com/v-code01/super-weights-kquant