Best LLM for every budget, updated daily(bestmodelforyourbudget.terrydjony.com)

127 points by terryds 1 month ago | 80 comments

Interactive chart plotting LLMs on the Artificial Analysis Intelligence Index against blended API price, highlighting the value frontier with filters.

AI PCs Aren't Good at AI: The CPU Beats the NPU(github.com)

450 points by dbreunig 2 years ago | 257 comments

GitHub repository from Useful Sensors with code to run and benchmark matrix-multiplication models on Qualcomm NPUs in Windows PCs, comparing them against the CPU and Nvidia GPUs.

Show HN: Benchi – A benchmarking tool written in Go(github.com)

45 points by lmazgon 1 year ago | 4 comments

A comparison of Ada and Rust, using solutions to the Advent of Code(github.com)

281 points by andsoitis 1 year ago | 196 comments

Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration(github.com)

93 points by noahkay13 8 months ago | 26 comments

Tieredsort: Header only, blazing fast (3-4x) C++17 sorting for numeric types(github.com)

7 points by signa11 10 months ago | 4 comments

Show HN: AI SRE Arena, an Open Benchmark for AI SRE Agents on Kubernetes(github.com)

14 points by emrahsamdan 17 days ago | 4 comments

GitHub repository for Project Arena, a vendor-neutral Kubernetes incident benchmark for evaluating AI SRE investigation tools with an AI judge.

Show HN: An open source framework for voice assistants(github.com)

320 points by kwindla 2 years ago | 34 comments

GitHub repository for Pipecat, an open source Python framework for building real-time voice and multimodal conversational AI agents.

Show HN: NanoMuse – An open-source AI agent for your phone and computer(github.com)

49 points by ilreb 19 days ago | 13 comments

GitHub repository for nanoMuse, an open-source personal AI agent that runs across Android, iOS, desktop, and browser and can operate your phone and computer.

Show HN: JevBench, a reproducible benchmark for typed decision models(benchmarkheaven.com)

119 points by florianstandhar 1 month ago | 32 comments

Benchmark Heaven's JevBench v1.3.0 leaderboard page ranking 52 Jev-class typed decision models on intelligence, calibration, speed and cost across 534 decisions.

Show HN: Made an open-source Lego AI generator(github.com)

114 points by antelocnova 23 days ago | 44 comments

GitHub repository for ldraw-nova, open-source agent tooling that uses LLMs to generate LEGO CAD models in the LDraw format, packaged as a dockerized web app.

Show HN: PhreshOS – OS for Web Apps(github.com)

6 points by zouhirdx 24 days ago | 2 comments

GitHub repository for PhreshOS, an MIT-licensed open-source browser-based desktop system that hosts web apps as Node.js threads with built-in auth and real-time communication.