X：Unsloth (@UnslothAI)· @NVIDIARobotics·· 2026-09-01AI 评分
NVIDIA Jetson AI Lab 教程：用 Unsloth 与 QLoRA 在 Jetson 上微调并量化模型
RT by @UnslothAI: ⚡ Fine-tune and quantize AI models directly on NVIDIA Jetson. Our new Jetson AI Lab tutorial shows how to use Unsloth and memory-efficient QLoRA to customize models, export quantized GGUF files, and run them locally with llama.cpp. Follow hands-on examples for: 🔹 NVIDIA Nemotron 3.5 Lightning on Jetson AGX Thor 🔹 Qwen3.5-4B on Jetson Orin Nano Start optimizing: https://nvda.ws/45YagAq
NVIDIA Jetson AI Lab 发布新教程，演示如何用 Unsloth 和内存高效的 QLoRA 直接在 NVIDIA Jetson 上微调与量化 AI 模型，导出量化 GGUF 文件并用 llama.cpp 本地运行。
来源：X：Unsloth (@UnslothAI) · x.lingyaoai.com