# yibie/strata-mlx

> An unofficial MLX inference engine for Apple Silicon that loads Strata's GSQ-RCO GGUF files and speaks its line protocol, so Strata's server and web UI can drive a 125B MoE model on a Mac.

- Magnitude: 1.1 out of 10 — Steady
- Stars: 92 total · +0 stars measured 2026-10-16, 00:05–01:38 UTC, ≈ 5 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-10 · Last push: 2026-10-15
- GitHub: https://github.com/yibie/strata-mlx · Page: https://gitnova.dev/en/r/yibie/strata-mlx

## Useful for

- Serve a large MoE GGUF model on Apple Silicon through Strata's line protocol
- Run 128K-token conversations with draft-and-verify speculative decoding in MLX
- Offload part of the experts to SSD on Macs with less unified memory than the model

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:05–01:38: 92 → 92 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +5 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 92 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #178.

## 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: 13
- Issues and pull requests: 11
- Watchers: 2
- Average over the last week: 14 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

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

2026-10-10 … 2026-10-16: 26, 21, 15, 16, 8, 6, 0

## Spotted in now

- Top new repositories this week: #178

## Similar by description

1. **Niko1221/Strata** — 4.3 · Cooling · Language models · C++ · +49 stars measured 2026-10-16, 00:06–01:31 UTC, ≈ 658 by evening
   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.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.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 2026-10-16 01:42 UTC, updated every 30 minutes.