AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Ultra-low-bit language models can reduce storage and memory bandwidth, but a nominal "1.58-bit" label does not fully describe the stored representation, retained capability, or runtime behavior. We study an end-to-end post-training conversion of Qwen, an instruction-tuned 4B-parameter model, using KOTMS rotation, E2M-ATQ ternarization, and GPTQ-style error compensation from TWLA. The experiment is weight-only: activations remain at 16-bit precision, so ILA-AMP is omitted. We evaluate effective bit accounting, task capability retention, perplexity, calibration sensitivity, checkpoint compositio

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T05:51:54.566Z. This is not the publication date.