BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

SEPTQ Proposes Post-Training Quantization Paradigm

Sep 13, 2026

The SEPTQ paper proposed a post-training quantization method intended to preserve generative quality on resource-constrained devices.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

Also covering this

Optimal Post-Training Quantization Scales and Where to Find Them — Large Language Modelsawesomepapers.io, Sep 13

More in Open-weight & owned stack

Z.ai publishes GLM-5.3 open weightsSep 8MiniMax H3 highlighted as open-weight multimodal modelSep 7InternLM releases 397B multimodal Intern-S2 modelSep 13DeepSeek Model Nearly Matches GPT-6 Astra DesignSep 10DeepSeek presents V4 FlashSep 8