# VecSzn/PolyStrata

> PolyStrata runs large AI models locally on a normal PC, with one-click install for Windows and Linux and an OpenAI/Anthropic-compatible API on localhost. It supports six models (Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder) on two inference engines, including image input.

- Magnitude: 3.2 out of 10 — Early signal
- Stars: 104 total · +1 star measured 2026-10-12, 15:50–17:25 UTC, ≈ 4 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: MIT · Created: 2026-10-06 · Last push: 2026-10-12
- GitHub: https://github.com/VecSzn/PolyStrata · Page: https://gitnova.dev/en/r/VecSzn/PolyStrata

## Useful for

- Run a local LLM server with an OpenAI-compatible endpoint for your own apps
- Connect Claude Code or another coding agent to a locally hosted Qwen3.6 model
- Send images to a local vision-capable model for description or analysis

## Why it’s here

- Star-counter measurements on 2026-10-12 (UTC), 15:50–17:25: 103 → 104 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +4 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 104 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- About 9 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 20
- Issues and pull requests: 12
- Watchers: 4
- Average over the last week: 14 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v0.1.42-poly.3 (2026-10-12)

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-06 … 2026-10-12: 0, 0, 0, 14, 42, 37, 1

## Similar by description

1. **Neroued/ninfer** — 2.5 · Steady · Language models · C++ · +25 stars measured 2026-10-12, 00:16–17:27 UTC, ≈ 34 by evening
   NInfer is a from-scratch C++/CUDA inference engine for Qwen3.5 Dense and MoE models on a single NVIDIA RTX 5090. It serves text, image, and video prompts via a local CLI or OpenAI-/Anthropic-compatible HTTP APIs.
   Full card: https://gitnova.dev/en/r/Neroued/ninfer.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-12 17:36 UTC, updated every 30 minutes.