HNHacker News
TopNewBestAskShowJobs

alanzhuly

147 karma · joined February 7, 2022

Advancing on-device AI.

Personal website: https://www.alanzhuly.com/

submissionscomments

Hyperlink: On-device AI agent that searches and summarizes all your local files

hyperlink.nexa.ai·4 pts·alanzhuly·
0

Qwen3-VL-4B and 8B runs locally on NPU, GPU, and CPU with one SDK

nexa.ai·3 pts·alanzhuly·
0

We Ran OpenAI GPT-OSS 20B Locally on a Phone

nexa.ai·2 pts·alanzhuly·
0

GPT-OSS 20B running on a phone

simonwillison.net·2 pts·alanzhuly·
0

Matthew McConaughey says he wants a private LLM on Joe Rogan Podcast

twitter.com·4 pts·alanzhuly·
0

How to unify Gemma and Whisper to build a super fast local voice LLM

nexa.ai·2 pts·alanzhuly·
0

What you can do with tiny (1B/3B) LLMs in a local RAG system?

nexa.ai·1 pts·alanzhuly·
0

Benchmark GGUF model with ONE line of code

github.com·6 pts·alanzhuly·
1

Llama.cpp Now Part of the Nvidia RTX AI Toolkit

developer.nvidia.com·13 pts·alanzhuly·
1

Small Language Models: Survey, Measurements, and Insights

arxiv.org·1 pts·alanzhuly·
0

Show HN: We built a knowledge hub for running LLMs on edge devices

github.com·13 pts·alanzhuly·
0

Join Super AI Agent Hackathon at Stanford, Hosted by HuggingFace and Nexa AI

twitter.com·12 pts·alanzhuly·
0

Show HN: Use functional tokens for AI agents to simplify app workflows

nexa4ai.com·80 pts·alanzhuly·
10

Google confirms the leaked Search documents are real

theverge.com·275 pts·alanzhuly·
75

Recovering 4D World from Monocular Video

huggingface.co·3 pts·alanzhuly·
0

Privacy-Aware Visual Language Models

arxiv.org·3 pts·alanzhuly·
0

Transformers Can Do Arithmetic with the Right Embeddings

huggingface.co·1 pts·alanzhuly·
0

Aya 23: Open Weight Releases to Further Multilingual Progress

huggingface.co·2 pts·alanzhuly·
0

Feds add nine more incidents to Waymo robotaxi investigation

techcrunch.com·23 pts·alanzhuly·
6

Elon Musk's XAI Secures New Backing from Andreessen Horowitz, Sequoia and Tribe

ft.com·6 pts·alanzhuly·
4

Neuralink's First User Is 'Constantly Multitasking' with His Brain Implant

wired.com·1 pts·alanzhuly·
0

Octopus V4: a graph of language models

huggingface.co·4 pts·alanzhuly·
2