---
format: "aidr-story-markdown/v1"
id: "ec56b5eff9affb1c339e466ce0f8237f0117032663d5db85034279f9f2a19228"
canonical_url: "https://aidr.today/ec56b5ef?lang=vi"
title: "180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers"
lang: "en"
requested_lang: "vi"
available_langs: ["en"]
translation_fallback: "en"
fallback_fields: ["title","summary"]
published_at: "2026-11-18T00:00:00.000Z"
category: "Infra"
topics: ["inference"]
source_urls: ["https://huggingface.co/blog/moe-expert-streaming"]
summary: "We’re on a journey to advance and democratize artificial intelligence through open source and open science."
---

# 180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

> [Open the canonical story](<https://aidr.today/ec56b5ef?lang=vi>)

**Published:** 2026-11-18T00:00:00.000Z
**Category:** Infra
**Topics:** inference

_English fallback used for: title, summary._

## Summary

We’re on a journey to advance and democratize artificial intelligence through open source and open science\.

## Sources

- [Story source](<https://huggingface.co/blog/moe-expert-streaming>)

