Skip to content
RankShark

Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.

ModelOpen sourceby Tencentsince 2026
30.1

SharkScore

#291 in Models

Why it scores 30.1

Hy-MT2-30B-A3B has a SharkScore of 30.1/100, ranked #291 of 608 in Models (updated 2026-11-19).

Each part compares Hy-MT2-30B-A3B with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
0 · 30%
User reviews
no data · 25%
Maintenance
28 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Hy-MT2-30B-A3B

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Hy-MT2-30B-A3B is Tencent’s multilingual translation model; the OpenRouter listing shows an 8,192-token context and usage-based token prices. [E1, E2]

A Tencent 30B-A3B mixture-of-experts model designed for multilingual translation. Its model page gives instructions for translation tasks and deployment with Transformers, vLLM, and SGLang. [E1]

Best for

  • Teams translating text among the languages supported by the model. · model card
  • Translation workflows that need terminology, style, context, structured-data, or delimiter instructions. · model card
  • Developers looking to run the model with Transformers, vLLM, or SGLang. · model card

Not for

  • Workloads that need more than the listed 8,192-token context window. · OpenRouter

Key features

  • Multilingual translation. The vendor says the Hy-MT2 family supports translation among 33 languages. · model card
  • Translation instructions. The vendor provides examples for terminology, style, personalization, contextual information, delimiters, and structured data. · model card
  • Model size and type. The vendor identifies this model as 30B-A3B and describes it as a mixture-of-experts model. · model card
  • Deployment options. The vendor provides deployment instructions for Transformers, vLLM, and SGLang. · model card
  • Fine-tuning. The vendor says its training pipeline supports full-parameter and LoRA fine-tuning. · model card

Pros

  • The model page lists translation support across 33 languages and gives examples for several kinds of translation instructions. · model card
  • The vendor provides deployment guidance for Transformers, vLLM, and SGLang. · model card
  • The OpenRouter listing provides input and output token prices and states the context and maximum completion sizes. · OpenRouter

Cons

  • The OpenRouter listing gives an 8,192-token context window and a maximum completion of 4,096 tokens. · OpenRouter
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter usage-based listing$0.074 per million input tokens; $0.295 per million output tokens8,192-token context window; maximum completion of 4,096 tokens

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Hy-MT2-30B-A3B; the vendor describes it as a 30B-A3B mixture-of-experts model. · model card
API
The OpenRouter listing includes chat completions, completions, messages, and responses endpoints. · OpenRouter
SDKs
The model page gives Transformers instructions and deployment instructions for vLLM and SGLang. · model card
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
Not stated (checked 18 Nov 2026)
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
8,192 tokens
Price per million tokens (OpenRouter listing) · now
$0.074 in, $0.295 out
Package downloads · 30 days
5,270
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Hy-MT2-30B-A3B

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source