Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-13 · source-backed
KronQ folds gradient covariance into the pipeline, using bidirectional incoherence processing and a Hessian-trace sensitivity metric for mixed-precision allocation (arXiv:2607.07964, COLM 2026). At aggressive 2-bit weight-only quantization it reaches 7.93 WikiText-2 perplexity while GPTQ and GPTAQ diverge into degenerate output past 2000 perplexity. For anyone fitting a 70B onto constrained local hardware, this is real evidence that usable 2-bit is getting close. The difference between 7.93 and "degenerate garbage" is the difference between local inference being viable and not.
Each link below shares sources, entities, or timing with this story.
Meta released Llama / Shared entity: Llama / Earlier coverage
Linked by a graph relationship (Meta released Llama); both cover Llama; earlier Llama coverage from 2026-06-15.
Linked by a graph relationship (Meta released Llama); both cover Llama; earlier Llama coverage from 2026-05-02.
Linked by a graph relationship (Meta released Llama); both cover Llama; earlier Llama coverage from 2026-05-01.
Linked by a graph relationship (Meta released Llama); both cover Llama; earlier Llama coverage from 2026-04-02.
Linked by a graph relationship (Meta released Llama); both cover Llama; earlier Llama coverage from 2026-03-12.
Meta released Llama / Same source domain
Linked by a graph relationship (Meta released Llama); reported by the same outlet (arxiv.org).
Linked by a graph relationship (Meta released Llama); reported by the same outlet (arxiv.org).
Meta released Llama / Shared topic
Linked by a graph relationship (Meta released Llama); overlapping topics (anyone, between).