SPIN Unprocessed
Source arXiv Artificial Intelligence export.arxiv.org Analyst
September 3, 2026 ai_technology research

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

View original on arxiv.org

Overview

arXiv:2609.01962v1 Announce Type: new Abstract: 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

SpinGraph analysis pending — check back after processing.

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

More from arXiv Artificial Intelligence

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO