# Hugging Face — Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

- Company: Hugging Face (huggingface.co)
- Announced: 2026-09-21T13:44:34+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/MultiverseComputingCAI/pruning-llms-like-a-physicist-block-removal-as-an
- Record: https://forck.live/items/12709-pruning-llms-like-a-physicist-block-removal-as-an-ising-optimization-problem
- Subject: Platform
- Models affected: Llama-3.3-70B-Instruct

Hugging Face and Multiverse Computing published a research paper proposing a physics-inspired approach to pruning large language models by reformulating block removal as a constrained binary optimization problem mapped to an Ising glass. The method achieves significant compression gains, reaching 23 percentage points improvement on MMLU over competing block-removal methods at 50% compression of Llama-3.3-70B-Instruct.

## Evidence

Verbatim from https://huggingface.co/blog/MultiverseComputingCAI/pruning-llms-like-a-physicist-block-removal-as-an:

> at 50% compression of Llama-3.3-70B-Instruct, we gain almost 23 percentage points on MMLU over the best competing block-removal method.

---

Record: https://forck.live/items/12709-pruning-llms-like-a-physicist-block-removal-as-an-ising-optimization-problem
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md