# Tencent-Hunyuan/Hy-MT2

> Tencent's Hy-MT2 family of multilingual translation models (1.8B, 7B, 30B-A3B MoE) supporting 33 languages and translation instruction following; includes the IFMTBench benchmark and quantized GGUF builds for local deployment.

- Magnitude: 5.6 out of 10 — Early signal
- Stars: 1,164 total · +3 stars measured 2026-10-09, 11:36–13:09 UTC, ≈ 44 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-05-18 · Last push: 2026-08-26
- GitHub: https://github.com/Tencent-Hunyuan/Hy-MT2 · Page: https://gitnova.dev/en/r/Tencent-Hunyuan/Hy-MT2

## Useful for

- Run Hy-MT2-1.8B-GGUF locally via llama.cpp to translate text without cloud access
- Translate UI strings in JSON while preserving keys and placeholders using the Structured Data instruction
- Evaluate instruction-following translation quality with the IFMTBench benchmark

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 11:36–13:09: 1161 → 1164 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +44 stars, using observed gains and the previous day.
- Before this, the repository barely got any stars — about 2 per day.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #4, +147 stars.
- About 23 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: 111
- Issues and pull requests: 17
- Watchers: 7
- Average over the last week: 74 per day
- Usual pace: 3 per day
- Stars in the last hour (measured): 3

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-10 … 2026-10-09: 0, 3, 3, 3, 2, 3, 9, 6, 9, 10, 7, 2, 4, 2, 6, 1, 2, 1, 4, 0, 3, 3, 5, 1, 2, 3, 2, 265, 202, 3

## Spotted in now

- GitHub Trending Python today: #4, +147 stars

## Similar by description

1. **TokenRhythm/NeoHorse** — 1.4 · Cooling · Language models · Python · +13 stars measured 2026-10-09, 00:12–13:19 UTC, ≈ 24 by evening
   The NeoHorse family of open-weight models for agent workflows: NeoHorse-1 (4B and 9B) for tool use, coding, and instruction following, and NeoHorse-Jev-4B which turns application state into structured decisions via prefill-only inference.
   Full card: https://gitnova.dev/en/r/TokenRhythm/NeoHorse.md
2. **wildminder/awesome-qwen-image** — 0.7 · Steady · Generative media · +2 stars measured 2026-10-09, 00:15–13:22 UTC, ≈ 4 by evening
   A curated list of resources for Qwen-Image 2.1, a 7B text-to-image and image-editing model: checkpoints, quantizations, LoRAs, prompt engines, and tooling.
   Full card: https://gitnova.dev/en/r/wildminder/awesome-qwen-image.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 2026-10-09 13:25 UTC, updated every 30 minutes.