# TileQuant preprint reports 2.66x generation throughput using mixed precision

_Published Friday, November 6, 2026 at 2:06 PM EST · AI, Science · Latest · Tier 2 — Notable_

Researchers introducing TileQuant report generation throughput of 2.66x the original model's in experiments with a training-free method that assigns different numerical precision to small blocks of language model weights.

Calibration identifies the most sensitive blocks, which remain at 16-bit precision while the rest use 8-bit. The execution kernel combines integer and 16-bit computation to reduce memory traffic. The preprint reports preserved quality across language modeling, reasoning, long-context retrieval and question answering, with results surpassing quantized and original models on multiple tasks.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2611.07217)

---
Canonical: https://techandbusiness.org/newswire/wjP8j5u-aCagGjAx5Jc6_j
Published: 2026-11-06T19:06:44.681Z
Story chronology: 2026-11-06T05:00:00.000Z
Retrieved: 2026-11-06T22:50:37.564Z
Publisher: Tech & Business (techandbusiness.org)