Paul Couvert(@itsPaulAi)
That's massive for local AI Google has just released Gemma 4 QAT and it runs with 3x less memory! ...
8.5Score
TL;DR · AI Summary
谷歌发布 Gemma 4 QAT 模型，内存占用减少 3 倍，可在手机和笔记本电脑上运行。
Key Takeaways
- Gemma 4 E4B 模型仅需 2GB RAM 即可在手机上运行。
- Gemma 4 31B 模型性能接近 Opus 4，可在笔记本电脑上运行。
- Gemma 4 QAT 模型内存占用减少 3 倍，推动本地 AI 发展。
Outline
Jump quickly between sections.
Mindmap
See how the topics connect at a glance.
查看大纲文本（无障碍 / 无 JS 友好）
- Gemma 4 QAT 模型
- 内存优化
- 内存占用减少 3 倍
- Gemma 4 E4B 模型
- 手机运行，2GB RAM
- Gemma 4 31B 模型
- 性能接近 Opus 4，笔记本运行
Highlights
Key sentences worth saving and sharing.
Gemma 4 E4B 模型仅需 2GB RAM 即可在手机上运行，性能优于 GPT-4o。
Gemma 4 31B 模型性能接近 Opus 4，可在笔记本电脑上运行。
Gemma 4 QAT 模型内存占用减少 3 倍，推动本地 AI 发展。
#AI#Gemma#Google#本地 AI
Open original articlePaul Couvert on X: "That's massive for local AI Google has just released Gemma 4 QAT and it runs with 3x less memory! Remember GPT-4o? Gemma 4 E4B is better and can now run on your phone (!!) with just 2GB RAM. And Gemma 4 31B (~ Opus 4 level) can now run on your laptop. https://t.co/I2RCXm3Hrg" / X
Paul Couvert
@itsPaulAi
That's massive for local AI Google has just released Gemma 4 QAT and it runs with 3x less memory! Remember GPT-4o? Gemma 4 E4B is better and can now run on your phone (!!) with just 2GB RAM. And Gemma 4 31B (~ Opus 4 level) can now run on your laptop.
7:02 PM · Jun 5, 2026
78.2K
Views
6
1
61
3
4
134
.
2
K
1.2K
7
0
706
Read 61 replies