Hy-MT2-30B-A3B
Tencent · · 27 days after Hy3 preview
Verified
1 of 1 published values traced to a source2 primary sources, 2 archived2 not disclosed by the lab
Why this status
Newly added. Sources are not archived and no value has been traced to one yet — run `npm run enrich`.
What these states mean · How records are judged · Has this record changed?
The largest of three multilingual translation models Tencent open-sourced together as Hy-MT2 on 2026-05-21, a Mixture-of-Experts model by its name.
Details
| Released | May 21, 2026stated in huggingface.coHy-MT2-30B-A3B was released on May 21, 2026.
|
|---|---|
| Company | Tencent |
| Family | Hy |
| Released alongside | Hy-MT2-1.8B · Hy-MT2-7B |
| Era | Agentic systems |
| Type | Language model · LLM |
| Modalities | Not recorded |
| Capabilities | Multilingual |
| Weights | Open weights |
| Licence | Apache-2.0 |
| Context window | Not disclosed |
| Parameters | Not disclosed |
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
- Weights and model card Hugging Face ↗
Sources
Record status: verified · confidence 90/100 · 2 of 2 primary
Newly added. Sources are not archived and no value has been traced to one yet — run `npm run enrich`.
- github.com Code repository archived
- huggingface.co Model card archived
Primary means published by the organisation that made the model. Verified records require at least one.
Hy family
- Hy3 preview April 24, 2026
- Hy-MT2-1.8B May 21, 2026
- Hy-MT2-7B May 21, 2026
- Hy-MT2-30B-A3B May 21, 2026
- Hy3 July 6, 2026
- Hy4 preview August 28, 2026
Compare Hy-MT2-30B-A3B with another model →
See Hy-MT2-30B-A3B on the interactive timeline →