unslothai/unsloth

OOM-ing on Nvidia Jetson Orin Nano

開放

#3,443 建立於 2025年10月13日

 (12 則留言) (0 個反應) (0 位負責人)Python (5,658 個分叉)batch import
help wanted

倉庫指標

星標
 (64,271 顆星)
PR 合併指標
 (PR 指標待抓取)

描述

I've installed unsloth from this index: https://pypi.jetson-ai-lab.io/jp6/cu126

The device has 8 GB of RAM/GPU, which should be enough for the following models: Gemma3 variants, 0.3B, 1B & 3B.

With ollama, I can easily do inference with all the above-mentioned models.

貢獻者指南