@Chuksdakingz: you can run Large LLMS on a USB drive or local hard drive platforms: mac, windows, linux and android models: > Gemma 4 …

X AI KOLs Timeline Tools

Summary

Guide on running large language models like Gemma 4, Qwen 3.5, and Gemma 2 on local devices via USB drive, no dependencies, only 8GB RAM required.

you can run Large LLMS on a USB drive or local hard drive platforms: mac, windows, linux and android models: > Gemma 4 E4B Ultra Uncensored Heretic (~5.34 GB) > Qwen 3.5 9B Uncensored Aggressive (~5.2 GB) > Gemma 2 2B Abliterated (~1.6 GB) > any downloadable huggingface model with .gguf weight when you unplug the usb drive, you unplug the llm > no dependencies > only 8GB of ram needed to run for 9B/16B models the video is the guide to install it.
Original Article
View Cached Full Text

Cached at: 06/25/26, 11:18 AM

you can run Large LLMS on a USB drive or local hard drive

platforms: mac, windows, linux and android

models:

Gemma 4 E4B Ultra Uncensored Heretic (~5.34 GB) Qwen 3.5 9B Uncensored Aggressive (~5.2 GB) Gemma 2 2B Abliterated (~1.6 GB) any downloadable huggingface model with .gguf weight

when you unplug the usb drive, you unplug the llm

no dependencies only 8GB of ram needed to run for 9B/16B models

the video is the guide to install it.

github:

my quant, learning from you dad

Similar Articles