Skip to content
AI Atlas
ModelActive

Hy-MT2-30B-A3B

Tencenthuggingface.co/tencent/Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

Open in Graph
data quality65

Updated 6 h ago · first seen 11 Sept 2026

model_01M294WVQTWSMC3A8182JMK80W

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 7 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Active parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    No

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Providers & Pricing1

All offers in the price terminal →
Current prices per 1M tokens
ProviderInput / 1MOutput / 1MCached inBatch in / outContextObservedSource
OpenRoutertencent/hy-mt2-30b-a3b$0.074$0.295——8.19K8 h agoopenrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of Hy-MT2-30B-A3B$0$0.10$0.20$0.30$0.40Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.295 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.29511 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Hy-MT2-30B-A3B$0$0.02$0.04$0.06$0.08$0.10Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.074 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.07411 Sept 2026

Hardware fit37

Estimated

36 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—17.8 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—17.8 GB est.Yes
Apple M2 Ultra4bit—17.8 GB est.Yes
Apple M1 Ultra4bit—17.8 GB est.Yes
Apple M3 Max4bit—17.8 GB est.Yes
Apple M4 Max4bit—17.8 GB est.Yes
Mac Studio (Apple M5 Max)4bit—17.8 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—17.8 GB est.Yes
Apple M2 Max4bit—17.8 GB est.Yes
Apple M1 Max4bit—17.8 GB est.Yes
Apple M4 Pro4bit—17.8 GB est.Yes
Mac mini (Apple M5 Pro)4bit—17.8 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—17.8 GB est.Yes
Apple M3 Pro4bit—17.8 GB est.Yes
Apple M1 Pro4bit—17.8 GB est.Yes
Apple M2 Pro4bit—17.8 GB est.Yes
Apple M44bit—17.8 GB est.Yes
iMac (Apple M4)4bit—17.8 GB est.Yes
Mac mini (Apple M6)4bit—17.8 GB est.Yes
MacBook Air (Apple M5)4bit—17.8 GB est.Yes
MacBook Pro (Apple M5)4bit—17.8 GB est.Yes
Apple M24bit—17.8 GB est.Yes
Apple M34bit—17.8 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB17.8 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB17.8 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB17.8 GB est.Yes
NVIDIA A100 80GB4bit80 GB17.8 GB est.Yes
NVIDIA H100 SXM4bit80 GB17.8 GB est.Yes
NVIDIA H100 NVL4bit94 GB17.8 GB est.Yes
NVIDIA DGX Spark4bit128 GB17.8 GB est.Yes
NVIDIA H2004bit141 GB17.8 GB est.Yes
NVIDIA H200 NVL4bit141 GB17.8 GB est.Yes
NVIDIA B2004bit180 GB17.8 GB est.Yes
AMD Instinct MI300X4bit192 GB17.8 GB est.Yes
AMD Instinct MI325X4bit256 GB17.8 GB est.Yes
NVIDIA DGX B2004bit1,440 GB17.8 GB est.Yes
Apple M14bit—17.8 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Papers1

Timeline4

Full timeline →
  • Release date changedModelHy-MT2-30B-A3BTencent

    Hy-MT2-30B-A3B: release date changed from 2026-05-11 to 2026-08-20

    Release date11 May 2026→20 Aug 2026openrouter
    openrouter.ai
  • Release date changedModelHy-MT2-30B-A3BTencent

    Hy-MT2-30B-A3B: release date changed from 2026-08-20 to 2026-05-11

    Release date20 Aug 2026→11 May 2026huggingface
    huggingface.co
  • New modelModelHy-MT2-30B-A3BTencent

    New model: Hy-MT2-30B-A3B (Tencent)

    openrouter
    openrouter.ai
  • Listed by providerModelHy-MT2-30B-A3BTencent

    OpenRouter lists Hy-MT2-30B-A3B at $0.074 in / $0.295 out per 1M tokens

    openrouter
    openrouter.ai

Change history35

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 12 Sept 2026 35 claims in force

Release date
11 May 2026
Openness
open-weights
License
Apache-2.0
Architecture
HYV3ForCausalLM
Parameters
30.1B
Active parameters
3B
Context window
8.19K tokens
Max output
4.1K tokens
Modalities
text
Input modalities
text
Output modalities
text
Languages
zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu, ur, te, mr, he, bn, ta, uk, bo, kk, mn, ug
File size
60.1 GB
Hugging Face repo
tencent/Hy-MT2-30B-A3B
Pipeline tag
translation
Downloads
22,074
Likes
497
Commercial use allowed
Yes
Derivatives allowed
Yes
Gated
No
Last modified
2026-07-21T12:22:53+00:00
Library name
transformers
Downloads all time
232,056
Model type
hy_v3
Openrouter id
tencent/hy-mt2-30b-a3b
Openrouter listed at
20 Aug 2026
Redistribution allowed
Yes
Structured output
Yes
Supported parameters
max_completion_tokens, max_tokens, response_format, stop, structured_outputs, temperature
Tags
transformers, safetensors, hy_v3, text-generation, translation, zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu
Tool calling
No
Weights available
Yes
Weights dtype
BF16, F32
35 claims · 30 properties

Release daterelease_date6

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
11 May 2026 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
20 Aug 2026 → supersededOpenRouter public model & pricing listingT2mediumdeterministic
11 May 2026 → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
20 Aug 2026 → supersededOpenRouter public model & pricing listingT2mediumdeterministic
11 May 2026 → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
20 Aug 2026 → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
apache-2.0 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
HYV3ForCausalLM → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
30.1B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Active parametersactive_parameter_count1

Claim history for Active parameters
ValueValid from → toStatusSourceConfidenceExtractor
3B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
8.19K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
4.1K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu, ur, te, mr, he, bn, ta, uk, bo, kk, mn, ug → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
60.1 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
tencent/Hy-MT2-30B-A3B → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
ValueValid from → toStatusSourceConfidenceExtractor
translation → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/tencent/Hy-MT2-30B-A3B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
22,074 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
497 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Gatedgated1

Claim history for Gated
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-07-21T12:22:53+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

Claim history for Library name
ValueValid from → toStatusSourceConfidenceExtractor
transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
232,056 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
hy_v3 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
tencent/hy-mt2-30b-a3b → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
max_completion_tokens, max_tokens, response_format, stop, structured_outputs, temperature → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
transformers, safetensors, hy_v3, text-generation, translation, zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16, F32 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

30

Source tiers

T230

Freshest observation

6 h ago

Conflicts

None

Source documents 4

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/tencent/Hy-MT2-30B-A3B model_pageT2· Quality secondary6 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=tencent&p=0&sort=downloads listingT2· Quality secondary6 h ago6
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary8 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/tencent/Hy-MT2-30B-A3B/raw/main/README.md model_cardT2· Quality secondary9 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (65/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →