Testing the GLM-4.5 Air Model: Writing Space Invaders in JavaScript on an Older Laptop
By
simonw
10mo ago· 4 min readenNews
95/100
Golden Brown
Bagelometer↗
Crisp on the outside, thoughtful on the inside. A keeper.
Score95TypenewsSentimentpositive
Summary
The article discusses the capabilities of the new GLM-4.5 Air model, an open-weight AI model from Z.ai, which excels in coding tasks. The author tested a 3bit quantized version of the model on a 2.5-year-old laptop and successfully used it to write a Space Invaders game in JavaScript. The model's performance and accessibility for users with 64GB machines are highlighted.
Key quotes
· 3 pulledThe models are pretty big—the smaller GLM-4.5 Air model is still 106 billion total parameters, which is 205.78GB on Hugging Face.
Ivan Fioravanti built this 44GB 3bit quantized version for MLX, specifically sized so people with 64GB machines could have a chance of running it.
I tried it out... and it works extremely well.
I wrote about the new GLM-4.5 model family yesterday—new open weight (MIT licensed) models from Z.ai in China which their benchmarks claim score highly in coding even against models such …
You might also wanna read
Z.ai Launches GLM-5.1 AI Model for Complex Agentic Coding Tasks
Z.ai has launched GLM-5.1, a next-generation AI model designed for complex agentic coding tasks. The model excels at long-horizon coding wor
EXO Labs Runs Llama 2 AI Model on 1997 Pentium II Using BitNet Optimization
EXO Labs successfully ran a lightweight Llama 2 AI model on a 1997 Pentium II processor with only 128 MB of RAM by leveraging BitNet's terna
