Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution

arXiv 2609.09240v112eb7d96b756ffe8ecea3bf74a925efaaecbac4bd858c9905a11aa1527ba4e23

Paper metadata

arXiv ID
2609.09240
Version
v1
Category
cs.AI, cs.LG
Authors
Anirudh Malik, M Sparsh Mehra, Poojith Devan
Publication date
2026-09-10T04:00:00Z
Source identifier
2609.09240v1
Public record ID
record:sha256:12eb7d96b756ffe8ecea3bf74a925efaaecbac4bd858c9905a11aa1527ba4e23

Source license ↗

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.

Evidence and limitations

Source ID
arxiv_research
Record identifier
12eb7d96b756ffe8ecea3bf74a925efaaecbac4bd858c9905a11aa1527ba4e23
Record type
Source metadata

This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.

Record · Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution · Baitaphish