Trendoday

QDA: Closed-Loop LLM Quantization Design with Agents

Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesig

  • Upvotes6
–Rank now
#11Peak rank
2Days on list
217Score · 7d
Nov 19, 2026First seen
Rank · 7 days

About this paper

Post-training quantization is the standard way to serve large language models at low cost. However, the best quantization recipe differs across models and precisions. As a result, experts must redesign it for every new model, which is time-consuming and often sub-optimal. Fortunately, an LLM agent can take over this design by refining the recipe over rounds of building and evaluating candidates, so that more rounds lead to better recipes. However, evaluating one quantized reasoning model takes tens of GPU-hours, and combining methods from different codebases means porting each to the new architecture by hand. We present QDA, a system in which an agent designs the recipe for each model and…

Upvotes
6
Authors
4
Published
Nov 17, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

QDA: Closed-Loop LLM Quantization Design with Agents was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 12 checks on 2 different days. Its best position was #11 of 30, reached on Nov 19, 09:29 UTC. It dropped off the list after Nov 20, 01:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 03:2808:5914:2919:5901:29 Nov 19, 03:28 UTC · #23Nov 19, 05:28 UTC · #16Nov 19, 07:29 UTC · #14Nov 19, 09:29 UTC · #11Nov 19, 11:29 UTC · #12Nov 19, 13:29 UTC · #13Nov 19, 15:29 UTC · #13Nov 19, 17:29 UTC · #11Nov 19, 19:29 UTC · #13Nov 19, 21:29 UTC · #13Nov 19, 23:29 UTC · #13Nov 20, 01:29 UTC · #13

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

04812 03:2808:5914:2919:5901:29 Nov 19, 03:28 UTC · 6Nov 19, 05:28 UTC · 8Nov 19, 07:29 UTC · 8Nov 19, 09:29 UTC · 9Nov 19, 11:29 UTC · 9Nov 19, 13:29 UTC · 9Nov 19, 15:29 UTC · 10Nov 19, 17:29 UTC · 12Nov 19, 19:29 UTC · 12Nov 19, 21:29 UTC · 12Nov 19, 23:29 UTC · 12Nov 20, 01:29 UTC · 12

Questions

Is QDA: Closed-Loop LLM Quantization Design with Agents trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 20, 01:29 UTC, after 2 days of trending.

What is the highest rank QDA: Closed-Loop LLM Quantization Design with Agents reached?

#11 on Hugging Face · Daily papers, on Nov 19, 09:29 UTC. Trendoday checks this list every 120 minutes.

How long has QDA: Closed-Loop LLM Quantization Design with Agents been trending?

It was first seen on Nov 19, 2026 and has been on the list on 2 days (12 checks) since.