Top New Best Ask Show Jobs

BUFU

646 karma · joined October 28, 2024

submissions comments

Qualcomm acquires Nexa AI, open-sources GenAI runtime for Hexagon NPUs

github.com·5 pts·BUFU·

We Ran GPT‑OSS 20B Local on a Phone

nexa.ai·1 pts·BUFU·

Qwen3-VL-30B-A3B-Instruct and Thinking

huggingface.co·6 pts·BUFU·

New Engine to Run SOTA AI Models on Qualcomm NPU Across Phone, PC, Cars, and IoT

nexa.ai·1 pts·BUFU·

First vision language model built off Open AI GPT-OSS

huggingface.co·3 pts·BUFU·

First Multimodal AI Model Designed for NPUs

huggingface.co·1 pts·BUFU·

Nexa AI Blogs

nexa.ai·1 pts·BUFU·

LFM2-VL: Efficient Vision-Language Models

liquid.ai·3 pts·BUFU·

Stanford CS336 Language Modeling from Scratch

youtube.com·19 pts·BUFU·

Ollama's new app

ollama.com·560 pts·BUFU·

You can now connect a directory of apps and tools to Claude with one click

claude.ai·2 pts·BUFU·

Ask HN: What tools have you tried to run AI locally on mobile?

2 pts·BUFU·

A C++ library to efficiently run Gemma-3N across various platform

github.com·5 pts·BUFU·

The Trump-Musk feud has been great for X, which jumped up the App Store charts

techcrunch.com·6 pts·BUFU·

How we’re responding to The NYT’s data demands in order to protect user privacy

openai.com·284 pts·BUFU·

ChatGPT Deep Research connects cloud apps

twitter.com·1 pts·BUFU·

Local AI generates highly realistic dialogue from a transcript

yummy-fir-7a4.notion.site·3 pts·BUFU·

Shroud's Spectre Divide and its developer are shutting down

theverge.com·1 pts·BUFU·

What Went Wrong with Skype?

theverge.com·4 pts·BUFU·

Anthropic's Recommendations to OSTP for the U.S. AI Action Plan

anthropic.com·3 pts·BUFU·

Quantized DeepSeek R1 Distill Models with Original Model Accuracy

nexa.ai·2 pts·BUFU·

Multimodal Model Quantization Support Through LLM Compressor by Neural Magic

neuralmagic.com·1 pts·BUFU·

DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks

huggingface.co·39 pts·BUFU·

NexaQuant: Llama.cpp-Compatible Model Compression with 100%+ Accuracy Recovery

nexa.ai·3 pts·BUFU·

Meta's new Video Understanding Multimodal Model used Qwen model for training

arxiv.org·7 pts·BUFU·

Llama.cpp Now Supports Qwen2-VL (Vision Language Model)

github.com·155 pts·BUFU·

OmniAudio-2.6B: Fastest Audio Language Model for Edge Deployment

nexa.ai·2 pts·BUFU·

Moondream 0.5B: The Smallest Vision-Language Model

moondream.ai·14 pts·BUFU·

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

arxiv.org·2 pts·BUFU·

What happens if we remove 50 percent of Llama?

neuralmagic.com·231 pts·BUFU·

Page 1 of 2Next →