arXiv (All)
open access
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM#639713
- JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization#1118313
- ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs#1155194
- TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers#1035107
- Why Does Post-Training Quantization Work?#673514
Record · ID 926940
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive