Home› Projects› PolyStrata
PolyStrata
C++

PolyStrata

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 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux,

by simplexai-labs · GitHub
Stars
Forks
License
Created
Last commit
Language
Likely
Self-hostable
anthropic-apicudagemmaMITC++Self-hostable
View on GitHub
In plain words

Run large AI models directly on your computer to perform various tasks without needing an internet connection.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
PolyStrata — GitHub preview card
📈 Star history
1.0k0.8k
2026-11-042026-11-15
📈 Track PolyStrata

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux,

PolyStrata has 1k stars on GitHub. It has been forked 135 times. PolyStrata is written mainly in C++. It has been in active development since 2026. PolyStrata is available under the MIT license. Its main topics are anthropic-api, cuda, gemma, gguf.

❓ Frequently asked questions

What is PolyStrata?

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 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux,

Is PolyStrata open source?

PolyStrata is an open-source project. It is released under the MIT license.

Is PolyStrata free?

Yes. PolyStrata is free and open source — you can use, modify and self-host it.

What license does PolyStrata use?

PolyStrata is available under the MIT license.

What language is PolyStrata written in?

PolyStrata is written mainly in C++.

🏅 Maintainer of this project?
olud.ai badge — PolyStrata

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=simplexai-labs-polystrata)](https://olud.ai/project/simplexai-labs-polystrata.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
project-maya
Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (42…
★ 2.9k · anthropic-api
sharesanthropic-apimixture-of-experts
TensorSharp
A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a co…
★ 632 · ai
sharesinference-engineglm
halogen-flash-server
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus sma…
★ 1.3k · amd
sharesspeculative-decodinginference-engine
BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on s…
★ 840 · android
sharesmixture-of-expertsgemma
llama.cpp-v100
llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x…
★ 74 · cuda
sharesspeculative-decodingmixture-of-experts
xllm
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accel…
★ 1.6k · deepseek
sharesinference-engineglm
sndr_core_engine
SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA…
★ 133 · awq
sharesspeculative-decodinggemma
inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
★ 1.1k · apple-silicon
sharesmixture-of-expertsgguf
sonar
Large-scale LLM inference engine
★ 1.9k · api-rest
sharesspeculative-decodinginference-engine
Atomic-Chat
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offl…
★ 2k · ai-chat
sharesgemmagguf

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.