#mixture-of-experts (12 Repositories)
Ranked open-source repositories tagged with #mixture-of-experts, scored by pull request acceptance likelihood and maintainer engagement velocity.
39.3%
11.8h
12 repositories tagged #mixture-of-experts
Helldez/BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, lossless, on stock llama.cpp
NVIDIA/cudnn-frontend
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
EfficientMoE/MoE-Infinity
PyTorch library for cost-effective, fast and easy serving of MoE models.
NeelM0906/Mference
Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Small 276B, native Mac app, CLI, and OpenAI-compatible server.
giannisanni/pulsar
SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.
carloslfu/slotstream
Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.
leonickson1/Swiftlet
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
mw00/project-maya
Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
peonist-ai/halogen-flash-server
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
DingoOz/llm-visuals
Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)
lucidrains/soft-moe-pytorch
Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch