A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.** Betelgeuse keeps dense computation on the GPU and brings routed experts into a bounded VRAM pool only when needed.
☆41Oct 31, 2026Updated this week
Alternatives and similar repositories for Betelgeuse
Users that are interested in Betelgeuse are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8-Flash-Next IQ3_S on 12 GB VRAM + 32 GB RAM + NVMe: ~45-50 tok/s decode, 131k context, Strata unify fork☆19Oct 24, 2026Updated last week
- Tested Apple Mac Pro 6,1 FirePro D500 passthrough on Proxmox: VFCT/VBIOS discovery, QMP verification, and automatic cold-boot startup rec…☆15Oct 18, 2026Updated 2 weeks ago
- A stylized lightning strike VFX built with Three.js (Procedural bolt generation, ground cracks, sparks, and camera shake).☆15Mar 27, 2026Updated 7 months ago
- Run MoE models bigger than your RAM, without the speed cliff☆18Updated this week
- C++ library for AXI DMA with direct and scatter-gather support☆13Feb 22, 2022Updated 4 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Guarded, recoverable WordPress MCP automation for Elementor, Gutenberg, WooCommerce, content, and code - with backups, validation, and au…☆30Oct 26, 2026Updated last week
- Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. …☆20Sep 23, 2026Updated last month
- Self-hosted Qwen3.8-27B (FP8) inference with vLLM, KServe and Envoy AI Gateway on RTX 6000 PRo or 2× RTX 4080 Super☆18Sep 2, 2026Updated last month
- A patching tool to remove the numpy<2 constraint from official mediapipe wheels.☆11Jun 23, 2026Updated 4 months ago
- An AI-powered agent system generating and verifying Lean 4 code, translating natural language problems into formally proven programs usin…☆22May 30, 2025Updated last year
- Controlling/Use-case framework for accessing smart cards of the telematic infrastructure. API Documentation: https://swiftpackageindex.co…☆22Sep 25, 2026Updated last month
- MRS-Core provides a transparent, modular, reproducible reasoning substrate.☆11Feb 3, 2026Updated 8 months ago
- LLM inference in C/C++☆16Aug 28, 2026Updated 2 months ago
- A full, unpruned 177B MoE model at 11.5 tok/s on one 12 GB GPU. Expert streaming for llama.cpp, with the measurement harness and every de…☆23Oct 3, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- finetune method to create think/model/requires tags to allow LLMs to write programs for things they can calculate instead of hallucinatin…☆15Apr 8, 2026Updated 6 months ago
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.☆18Mar 20, 2026Updated 7 months ago
- LLM inference in C/C++☆79Oct 22, 2026Updated last week
- Turn a Windows 11 IoT LTSC PC into a couch gaming console: boots straight into Steam Big Picture, survives crashes, desktop only on deman…☆19Aug 24, 2026Updated 2 months ago
- X-Men Legends original Xbox to Windows recompilation feasibility project targeting Direct3D 8☆45Updated this week
- ChromeCast Arduino☆22Aug 29, 2013Updated 13 years ago
- Code for my collection of predictors/classifiers/etc☆14Jul 18, 2024Updated 2 years ago
- A parametric web app for making DIY air purifiers☆21Oct 22, 2026Updated last week
- Static recompilation of Rogue Galaxy (PS2) to a native PC executable, on PS2Recomp☆53Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Compact representations of placeholders for images based on https://blurha.sh/☆15May 18, 2020Updated 6 years ago
- .NET Commons☆16Dec 7, 2022Updated 3 years ago
- Wireless file sharing between Steam Deck and phone/PC☆17Oct 14, 2026Updated 2 weeks ago
- Extracts files, folders, or entire repos from a pasted Huggingface URL, and lets you queue and download them using HF's Xet file system, …☆22Sep 20, 2026Updated last month
- English, French, German, and Spanish swipe typing for KDE Plasma Keyboard on Wayland and Steam Deck gaming mode keyboard. Standalone Arch…☆18Updated this week
- ☆29Oct 11, 2026Updated 3 weeks ago
- Agentic control of Linux desktops over at-spi and text based primatives with visual analysis fallback. Control a linux desktop and run CI…☆15Oct 21, 2026Updated last week
- Coding agent where a 0.8B decision model works alongside Qwen 3.8-27B: Jeff takes the routine steps itself and decides when Qwen should t…☆28Oct 7, 2026Updated 3 weeks ago
- A simple markdown blog using GatsbyJS☆11Feb 20, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Fully local 2D/3D Asset generation☆122Updated this week
- Tandem work skills that push back on agent autonomy and give you control back: fewer unprompted antics, more actual collaboration.☆16Updated this week
- Temporal LoRA gating for LTX 2.3 workflows in ComfyUI.☆22Aug 4, 2026Updated 2 months ago
- Zone of the Enders - Static Recompilation Project for PC☆52Updated this week
- Tensor-Core selector unlock for RTX 4070 Ti Super☆29Oct 20, 2026Updated last week
- ☆65Updated this week
- A complete emulation setup for the Steam Deck: install emulators, transfer ROMs, add games to Steam, back up saves — all with a controlle…☆22Sep 29, 2026Updated last month