Can I run Hy-MT2-7B locally?

Yes, the weights are open and Tencent publishes GGUF variants for llama.cpp, so you can run it on your own hardware with tools like Ollama or LM Studio.

What does Hy-MT2-7B cost and what is its context limit?

Via API it is priced at $0.07 per million input tokens and $0.29 per million output tokens, with a context window of 8,192 tokens.

How does the 7B differ from the other Hy-MT2 sizes?

The family also includes a 1.8B model aimed at on-device use and a 30B MoE variant for higher-quality output; the 7B sits in the middle, balancing quality and hardware requirements for server or capable local deployment.

Hy MT2 7B

5086°

#llm #tencent #translation #multilingual #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Tencent | 8,192 token context | $0.07/M input, $0.29/M output. Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

How much VRAM do I actually need for local AI?

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Hy-MT2-7B is a 7-billion-parameter translation model from Tencent, purpose-built for machine translation across 33 language pairs plus Chinese dialect and minority-language pairs. It operates in a fast-thinking mode and handles structured, glossary-based, contextual, and style-guided translation workflows that general-purpose LLMs typically fumble. If translation quality and instruction-following in translation tasks are your priority, this is a more focused tool than reaching for a frontier chat model.

Known for

Covers 33 language pairs plus five Chinese dialect and minority-language pairs
Instruction-following translation: glossary, style, delimiter, and context-aware modes
Open weights with GGUF variants available for local deployment
Fast-thinking mode that Tencent claims outperforms larger open-source models on translation tasks
Part of a three-size family: 1.8B, 7B, and a 30B MoE variant

Watch out for

Context window is 8,192 tokens — not suited for translating long documents in a single pass.
Specialist translation model only; do not expect general reasoning, coding, or chat capability.
Licence terms are not detailed in what Tencent has published — check the repo before commercial use.

Best for

Translation

Multilingual

Runs locally

Prompts to try

Glossary-constrained translation

Translate the following English product description into French. You must use these glossary terms exactly: 'interface utilisateur' for 'user interface', 'tableau de bord' for 'dashboard', and 'flux de travail' for 'workflow'. Text: 'The new dashboard streamlines the user interface and simplifies complex workflow automation for enterprise teams.'

Style-guided translation

Translate the following English paragraph into formal written Spanish suitable for a legal contract. Preserve the formal register and do not simplify any terminology. Text: 'The parties agree that any dispute arising under this agreement shall be resolved through binding arbitration in accordance with the rules of the relevant jurisdiction.'

Contextual document translation

Translate the following customer support exchange from English to Simplified Chinese. The previous message established that the customer is asking about a refund for a delayed shipment. Maintain a polite, professional tone consistent with that context. Text: 'We sincerely apologize for the inconvenience. Your refund has been processed and should appear in your account within five to seven business days.'

Compare with

Hy-MT2-1.8B
Open-weights model
8,192 token context · $0.04/M input, $0.18/M output
Hy-MT2-30B-A3B
Open-weights model
8,192 token context · $0.07/M input, $0.29/M output
Saba
API-only model
32,768 token context · $0.20/M input, $0.60/M output
Hy4 preview
Open-weights model
1,048,576 token context · $0.83/M input, $2.50/M output

More text models from tencent

Questions people ask

Can I run Hy-MT2-7B locally?: Yes, the weights are open and Tencent publishes GGUF variants for llama.cpp, so you can run it on your own hardware with tools like Ollama or LM Studio.
What does Hy-MT2-7B cost and what is its context limit?: Via API it is priced at $0.07 per million input tokens and $0.29 per million output tokens, with a context window of 8,192 tokens.
How does the 7B differ from the other Hy-MT2 sizes?: The family also includes a 1.8B model aimed at on-device use and a 30B MoE variant for higher-quality output; the 7B sits in the middle, balancing quality and hardware requirements for server or capable local deployment.

Captain's verdict
A rare specialist: if translation is the actual job, Hy-MT2-7B is sharper and cheaper than routing the work through a general frontier model.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Hy MT2 7B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm tencent translation multilingual local

Browse by Model Family