unslothai/unsloth

OOM-ing on Nvidia Jetson Orin Nano

Open

#3,443 建立於 2025年10月13日

在 GitHub 查看
 (12 留言) (0 反應) (0 負責人)Python (5,658 fork)batch import
help wanted

倉庫指標

Star
 (64,271 star)
PR 合併指標
 (平均合併 3天 15小時) (30 天內合併 525 個 PR)

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