Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
IQ4_XS is the smallest standard 4-bit GGUF and had a tiled matmul kernel on Intel AMX, none on Arm. FastPath64 writes it: 2.12x prefill on Neoverse N2, 1.30x a whole agent turn, byte-identical output.
An Arm-optimized implementation of Qwen3-TTS focused on CPU inference efficiency, easier deployment, and real-world developer usability for cloud and edge Arm/x86 platforms.
World's fastest full-cycle processing at 3.82ns on standard ARM, zero overhead, self-reset in one shot
On-device Mobile AI benchmark for private offline message assistance with int8 optimization for Arm phones, tablets, and laptops.
Arm Cloud AI inference API with int8 optimization, batching, and benchmark proof for CPU-only cloud servers.
Building intelligent, hardware-assisted ransomware defense for ARM-based embedded systems through real-time detection and automated protection.
When monsoon clouds blind optical satellites, FloodSense-PK sees through them. SAR + AI + live river data = early flood warnings for millions of Pakistanis.
Catch AI inference regressions before they reach production.
prime
This is a framework , runtime + compiler allowing OpenCL C kernels to run on Android GPUs.
Cloud Cost optimizer
Teach your phone a sound in minutes, then recognize it privately and offline.
On-device voice notes, made into replayable decisions.
Imagine needing help, wanting to communicate, or having something to say, No one understands. Gestura transforms gestures into speech, empowering communication, independence, and confidence.
A CPU-friendly memory layer that compresses long agent workspaces into small, auditable prompt packs for Arm64 cloud deployments.
An open, model-agnostic, multi-track asynchronous reasoning harness and heuristic governor optimized for high-concurrency, low-latency execution on Arm64 architecture.
A cross-platform agentic coding harness for open-weight and local models — build, test, and review code privately, at your own cost. Runs natively on Arm64: clone and run it on any Apple Silicon Mac.
Browse research like TikTok—swipe through arXiv papers, translate as you read, ask questions, and keep learning in your spare moments.
PocketBrain gives AI models a smaller footprint and a faster future through intelligent optimization for Arm powered platforms.
SIGMA – Sovereign Human–AI Algorithmic Interaction System International Patent Application (PCT): PCT/SA2026/050007 Reference: SIGMA-ENG-2026
AI finance decision room where specialist agents turn messy company data into evidence-backed CFO recommendations.
High-speed local avoidance for single-board robots
An intelligent UAV that combines AI, thermal imaging, and embedded systems to detect survivors, avoid obstacles, and support real-time rescue missions.
The VS Code for Arm AI Optimization: an end-to-end platform with an AI Advisor, Auto SIMD NEON Kernel Generator, Replay Timeline Profiler, and Arm Performix v2.0 exporter for Arm64 CPUs.
265 – 288 of 333
