unslothai/unsloth

OOM-ing on Nvidia Jetson Orin Nano

Open

#3,443 创建于 2025年10月13日

在 GitHub 查看
 (12 评论) (0 反应) (0 负责人)Python (64,271 star) (5,658 fork)batch import
help wanted

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.

贡献者指南

技术栈
pythonpytorch
领域
performancemachine learning
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
active
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Python knowledgePyTorch basicsUnderstanding of GPU memory
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
50
研究方向
Investigate the model loading process in unsloth to identify where excess memory is allocated. Compare memory usage profiles between unsloth and ollama for the same model. Check if there are any memory saving options like offloading or quantization that can be enabled. Look at the issue comments for any suggestions from maintainers or other users.