NexaAI/nexa-sdk

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

27 best points · 6 comments · 5 Hacker News posts · 8,506 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Nexa SDK – Build powerful and efficient AI apps on edge devices (27 points, 4 comments, by frednoodle, 2024-09-08)
• Run Qwen 2.5 Family and Other LMs in GGUF Format from HF Locally (11 points, 1 comments, by unseenmars, 2024-09-18)
• Benchmark GGUF model with ONE line of code (6 points, 1 comments, by alanzhuly, 2024-10-24)
• Benchmark GGUF models with a ONE line of code (1 points, 0 comments, by jinqueeny, 2024-10-27)
• Benchmark GGUF models with a one line of code (1 points, 0 comments, by mountainview, 2024-11-01)