# TianyuCodings/NanoJev > A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake). - Magnitude: 0.3 out of 10 — Quiet - Stars: 2,562 total · Not enough measurements today - Star trust: star growth looks organic - Category: Language models · Language: Python · License: MIT · Created: 2026-09-17 · Last push: 2026-10-16 - GitHub: https://github.com/TianyuCodings/NanoJev · Page: https://gitnova.dev/en/r/TianyuCodings/NanoJev ## Useful for - Train a decision model for maze and Snake tasks using the provided pipeline - Compare NanoJev, Jev, and Untuned Qwen in the interactive side-by-side replay - Get probability distributions over 2–255 candidates in a single forward pass ## Why it’s here - There are not enough fresh counter measurements for today's UTC day. The gain is unknown. - The repository is 40 days old and already has 2,562 stars. - Recent forks include notable developers: @HonglinChu (360 followers). ## 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: 264 - Issues and pull requests: 16 - Watchers: 11 - Average over the last week: 2 per day - Usual pace: 18 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: 7, 8, 5, 7, 4, 11, 5, 8, 8, 5, 6, 7, 6, 1, 5, 6, 7, 4, 6, 3, 2, 0, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 10-14 1.0, 10-15 1.1, 10-16 1.5, 10-17 1.3, 10-18 1.0, 10-19 1.4, 10-20 1.5, 10-21 1.4, 10-22 1.1, 10-23 1.3, 10-24 1.0, 10-25 0.8, 10-26 0.3, 10-27 0.3 --- 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 2026-10-27 00:03 UTC, updated every 30 minutes.