Run MoE models bigger than your RAM, without the speed cliff
☆16Oct 16, 2026Updated this week
Alternatives and similar repositories for moe-cache
Users that are interested in moe-cache are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.☆52Oct 7, 2026Updated last week
- Qwen3.8-Flash-Next (MoE, NVFP4) and Qwen3.8-27B on two 16 GB consumer GPUs: two-GPU tensor parallel, experts offloaded to CPU. Formerly n…☆43Updated this week
- Strata port for Tesla V100 (sm_70): Qwen3.8-Flash-Next with 262K context and MTP☆84Updated this week
- Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples f…☆144Oct 11, 2026Updated last week
- Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the laye…☆101Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- High-performance universal media optimizer for images, video, and audio. Built with Nuitka and Go, with auto-GPU acceleration and crash-s…☆20Sep 13, 2026Updated last month
- Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith …☆303Updated this week
- A resilient world of actors for Rust: typed messages, supervision trees, death watch.☆36Updated this week
- Persistent memory for Claude Code, Claude Desktop, and Codex — save once, recall across sessions, shared across all your AI CLIs.☆17Oct 8, 2026Updated last week
- Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understandi…☆29Apr 23, 2026Updated 5 months ago
- Bits to communicate with an Anviz device☆13Jul 15, 2014Updated 12 years ago
- Photographs to a textured mesh on one 8 GB NVIDIA card, offline. Built on TRELLIS.2, with a four view path, and the photographs' own pixe…☆46Oct 11, 2026Updated last week
- Your hardware. Your rules. Your digital soul. A multimodal, local, and uncensored AI framework featuring autonomous PC control, ambient p…☆33Jul 28, 2026Updated 2 months ago
- Real-time monitoring for llama.cpp inference servers: a read-only host agent plus a web dashboard for hardware, health and inference tele…☆30Sep 26, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Engineer's vibe coding companion with 2.16" AMOLED ESP-32-S3 touch device, it has coding buddy for approval, usage limits, weather and li…☆24Oct 5, 2026Updated 2 weeks ago
- Solve proof-of-work challenges served by anubis.techaro.lol without a web browser☆13Oct 11, 2026Updated last week
- Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-…☆84Updated this week
- Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash, Mini…☆32Oct 7, 2026Updated last week
- Effects for any player on your phone. An iOS 27 audio output device running EffeTune's DSP.☆47Updated this week
- Deploy, monitor, and tune LLM through a visual interface — plus image / video generation on top of ComfyUI.☆103Oct 6, 2026Updated 2 weeks ago
- ROCm for gfx803 aka RX 460, RX 470, RX 480, RX 550, RX 560, RX 570, RX 580 and RX 590 with custom patches, kernel fixes, etc☆41Oct 6, 2026Updated 2 weeks ago
- Evidential Calibration☆11Mar 8, 2022Updated 4 years ago
- RTX 6000 96GB/Spark 128GB vLLM Recipe for Qwen 3.8 Flash Next☆22Sep 8, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT☆41May 2, 2026Updated 5 months ago
- Speech models and artifacts for voice2json☆14May 22, 2023Updated 3 years ago
- Professional Offline AI Workspace for ComfyUI☆41Oct 6, 2026Updated 2 weeks ago
- KDE Remote is a custom Android smart remote for Linux desktops, KDE Bigscreen, and media PCs, built on KDE Connect. It features a tactile…☆33Oct 7, 2026Updated 2 weeks ago
- Code for Paper "Evidential Softmax for Sparse MultimodalDistributions in Deep Generative Models"☆11Oct 25, 2021Updated 4 years ago
- Local Codex-style desktop GUI for the Pi coding agent☆32Jun 29, 2026Updated 3 months ago
- Kiln: an Android emulator for Apple Silicon Macs. Hardware virtualization, GPU acceleration (GLES/Vulkan), per-game key mapping. Beta.☆34Updated this week
- Wireshark dissectors for various proprietary Apple Bluetooth protocols☆47Jul 24, 2026Updated 2 months ago
- Kurento PHP client☆13Sep 10, 2015Updated 11 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.
- This kernel adds supports for running Docker on Sony Xperia 5 II (pdx206).☆10Mar 14, 2023Updated 3 years ago
- MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tok…☆25Updated this week
- ☆11Mar 10, 2022Updated 4 years ago
- A cinematic, dashboard-first Obsidian vault — glass bento dashboards, Open Library reading tracker, career pipeline, and a three.js lo-fi…☆36Aug 24, 2026Updated last month
- Skills for managing an Amazon seller account via SP-API, through the Amazon Selling Partner Connector (MCP). Write actions are always hum…☆31Updated this week
- Run unmodified native Apple-silicon macOS games on iPad (retag + UIKit shims)☆40Oct 8, 2026Updated last week
- ADHD-friendly personal execution OS: habits, study blocks, agent control (Hermes/MCP), local SQLite☆38Updated this week