Tabby – AI Coding Assistant Runs on Apple M1/M2 GPU
Tabby – AI Coding Assistant Runs on Apple M1/M2 GPU
Hi HN, after five months of hard work since Tabby's previous Show HN ( https://news.ycombinator.com/item?id=35470915 ), I'm thrilled to share you the release of Tabby v0.1.1. Previously, Tabby ran exclusively on CUDA devices, posing a significant barrier for developers looking to effectively utilize LLMs in their day-to-day coding. The Tabby team made a significant contribution by enhancing support for the StarCoder series models (1B/3B/7B) in llama.cpp. This enhancement allows these models to run on Metal, providing comparable performance to that of an NVIDIA GPU. I eagerly look forward to receiving feedback from the community and witnessing the enhanced on-edge deployment experience! References: [1] Apple Installation Instructions: https://tabby.tabbyml.com/docs/installation/apple/ [2] Launch blog: https://tabby.tabbyml.com/blog/2023/09/18/release-0-1-1-meta...
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
Read-only AI coding assistant
Sidekick – AI Coding Assistant
AiSyncing – Back up your AI coding assistant memories to GitHub
Magnet – free expert AI coding assistant with GPT-4
Superblocks AI – AI coding assistant for internal apps
A tiny (480 LOC) AI coding assistant for your shell
SwiftUI components + AI coding assistant
ARM – NPM for AI coding assistant resources
A local tool that logs every time you swear at your AI coding assistant
AI coding assistant on Mobile for OpenCode/KiloCode Server