Run a 35B MoE model at 10+ tok/s on a $600 Mac mini. Pure C/Metal inference engine streaming experts from SSD on Apple Silicon
☆21Apr 20, 2026Updated 6 months ago
Alternatives and similar repositories for flash-moe
Users that are interested in flash-moe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Wrap commands that might cause out-of-memory errors, and stop them before they freeze your machine☆15Sep 22, 2026Updated last month
- Meteor panel-layout boilerplate, using Iron-Router and Meteor UI.☆11Mar 27, 2015Updated 11 years ago
- Pi extension that tracks bash tool token usage with live stats, grouping, and export☆23Feb 10, 2026Updated 8 months ago
- MLX Model Quantization Toolkit - Comprehensive collection of Jupyter notebooks for converting and quantizing large language models usi…☆15Aug 16, 2025Updated last year
- An infinite canvas with AI-powered code terminals☆16Feb 15, 2026Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆18Mar 30, 2026Updated 6 months ago
- Instant Perfect Native MacOS Transcription☆56Jul 26, 2025Updated last year
- Inspector for Blaze templates☆20Aug 7, 2017Updated 9 years ago
- Universal REPL Bridge for LLMs - Tab completion, interactive prompts, TUI support☆20Nov 24, 2025Updated 10 months ago
- Fermion Research fork of llama.cpp: FV5/FV5B five-value ternary types for Neutrino GGUF packs (CPU + CUDA)☆14Sep 29, 2026Updated 3 weeks ago
- App-friendly Swift APIs for Apple's on-device Music Understanding framework.☆30Jul 10, 2026Updated 3 months ago
- Rust library implementing the Toorani-Beheshti signcryption scheme☆13Aug 15, 2023Updated 3 years ago
- A clean Android reader for self-hosted FreshRSS via the Google Reader API☆14Aug 7, 2026Updated 2 months ago
- https://pypi.org/project/deepagents-sandbox/☆29Apr 22, 2026Updated 6 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A command-line interface for Raindrop.io bookmark management.☆14Feb 17, 2026Updated 8 months ago
- Falcon Evaluate is an open-source Python library aims to revolutionise the LLM - RAG evaluation process by offering a low-code solution. …☆16Jan 31, 2024Updated 2 years ago
- The Source code of the demos, projects demonstrated as part of the London Agentic AI Meetup https://www.meetup.com/london-agentic-ai/☆18Apr 26, 2026Updated 5 months ago
- AutoGEPA automates the tedious parts of setting up a DSPy optimization pipeline: converting raw data into dspy.Examples, generating a met…☆19Jul 4, 2026Updated 3 months ago
- AI-powered tweet optimization tool using DSPy with hill-climbing algorithm☆29Oct 15, 2025Updated last year
- ☆13Aug 5, 2026Updated 2 months ago
- llms can learn their own context compression via RL☆51Nov 26, 2025Updated 10 months ago
- CHAOS - Chrome Agent OS: Multi-agent Chrome extension with intent tracking, context awareness, and sandboxed tool execution☆16Updated this week
- Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.☆15Apr 27, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- node-csv npm wrapped for meteor☆17Jul 29, 2015Updated 11 years ago
- Paste, and drag drop images to load them into Pi. Also works in tmux.☆12May 5, 2026Updated 5 months ago
- A minimalist agent harness☆17Feb 16, 2026Updated 8 months ago
- npm's top HTTP client, request, packaged for Meteor☆21Jul 30, 2016Updated 10 years ago
- Introspection dashboard for the pi coding agent — tools, prompts, skills, and the system prompt injected on init.☆40May 20, 2026Updated 5 months ago
- 🚀 A self-hosted AI PR reviewer.☆62Updated this week
- Tiny MLX-trained schedule model with a dependency-free WebGPU runtime☆16Sep 12, 2026Updated last month
- Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, sisyphus step gating, autoContinue, and an above-edit…☆21May 13, 2026Updated 5 months ago
- StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018☆12Aug 14, 2019Updated 7 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Your AI remembers now. Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. N…☆35Oct 2, 2026Updated 3 weeks ago
- Security scanning for AI Agents☆33Mar 28, 2026Updated 6 months ago
- LLMs4OL Challenge @ ISWC☆18Aug 18, 2026Updated 2 months ago
- Parses and Plots Illumina SAV files☆13Jan 30, 2019Updated 7 years ago
- A grumpy sidecar extension for pi that roasts slop, overbuilding, and risky changes.☆14Apr 3, 2026Updated 6 months ago
- Highly opinionated Pi harness.☆19Updated this week
- Let Auggie describe your PR for you☆10Oct 9, 2025Updated last year