Indras-Mirror/Xolotl
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A C++ inference engine and OpenAI/Anthropic-compatible server, forked from Strata, that runs large MoE models such as DeepSeek-V4.1-Flash (552B) on one 24 GB NVIDIA GPU by tiering expert weights across VRAM, pinned RAM and NVMe. Also supports GLM-5.3-Flash and Qwen3.8 models.
Who it's for
Linux developers running large local MoE LLMs on a single NVIDIA GPU with limited VRAM
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up Indras-Mirror/Xolotl in my project. Follow its README: https://github.com/Indras-Mirror/Xolotl. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
18,267 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/Indras-Mirror/Xolotl?ref=badge)Similar repos
- deepseek-ai/DeepInfer
Open-source offline inference framework for DeepSeek models, offering optimized kernels, MoE expert and attention parallelism, speculative decoding, asynchronous scheduling, deterministic sampling and
- mw00/project-maya
A C++ engine, server and dashboard for running the GLM-5.3-Flash and DeepSeek-V4.1-Flash models locally on one to sixteen NVIDIA or AMD GPUs, on Linux or Windows. It offers OpenAI- and Anthropic-compa
- Edge0-AI/Edge0
Open-source streaming MoE inference framework that runs large sparse-MoE models on consumer hardware by streaming expert weights from SSD on demand. A trained prerouter predicts expert routing one ste
- prabanta-dev/janas
A C inference engine for running large mixture-of-experts language models on ordinary computers, with or without a GPU. Weights stay on disk, and the experts each token needs are streamed from an NVMe
- VecSzn/PolyStrata
Runs large open-weight language models locally on a PC with NVIDIA GPUs, using a PolyStrata engine for several models and the Strata engine for Qwen3.8-Flash-Next. Offers OpenAI- and Anthropic-compati
- justxor/deepseek-local-guide-ru
A Russian-language guide for installing and running DeepSeek models locally on PC, Mac and servers. Covers Ollama, llama.cpp, LM Studio, vLLM, SGLang and Open WebUI, plus API usage, RAG, agents and fi