Niko1221/Strata

Qwen3.8-Flash-Next (125B MoE) on a 12-24 GB NVIDIA GPU + 64 GB RAM: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

Language modelsC++

4.5 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 26, 2026, 11:40 UTC.

Open on Seismograph Open on GitHub

About the project

A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.

Useful for

Run a private chat with a large model on your own PC without sending data to the cloud
Connect the local model as an OpenAI-compatible provider to a coding agent or script
Send a screenshot or scanned page to the model for recognition via image input

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

48 stars so far today, about 78 expected by the end of the day.
The spike has held for 3 days in a row — not a one-off blip.
The repository is 2 days old and already has 83 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #176.
About 10 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 83
Today: 48 · ≈ 78 by evening
Forks: 9
Issues and pull requests: 11
Watchers: 2
Language: C++
Latest release: v0.1.2 · September 25, 2026
Created: September 24, 2026
Last push: September 25, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 26, 2026Top new repositories this week: #176

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/Niko1221/Strata.svg?lang=en)](https://gitnova.dev/en/r/Niko1221/Strata)

Similar by description

1.0
AtomicBot-ai/Atomic-Chat
Desktop app and local inference engine for running open-weight LLMs (Llama, Gemma, Qwen, Mistral, etc.) on your own machine, exposing an OpenAI-compatible API at localhost:1337/v1.

SteadyLanguage modelsTypeScript+3 stars today, ≈ 5 by evening
2.5
incoai/splash
A local LLM inference engine for Apple silicon, specialized per model: serves OpenAI- and Anthropic-compatible APIs to coding agents on a single Mac.

CoolingLanguage modelsC+++12 stars today, ≈ 28 by evening
1.9
Neroued/ninfer
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.

CoolingLanguage modelsC+++7 stars today, ≈ 19 by evening
3.3
architectds/collabosm
A set of scripts to run Qwen3.8-Flash-Next (125B MoE) on a single Colab A100-80GB High-RAM with an OpenAI-compatible endpoint and measured throughput.

Early signalLanguage modelsPython+1 star today, ≈ 14 by evening
0.5
EricLBuehler/mistral.rs
A Rust LLM inference engine with automatic model loading, multimodality (text, image, video, audio), quantization, and an OpenAI/Anthropic-compatible server.

SteadyLanguage modelsRust+0 stars today, ≈ 0 by evening
1.0
APUS-AI-Lab/fast-browser-use
A local browser automation engine powered by Qwen3.5 via MLX or PyTorch: it picks actions from visible DOM elements in a single forward pass instead of text generation. Runs fully offline with no cloud APIs.

CoolingAI agentsPython+1 star today, ≈ 3 by evening