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...
Updated 25 min ago · first seen 11 Sept 2026
model_01M294WVQTWSMC3A8182JMK80W
- Parameters
- 30.1B · 3B active
- T2 · 3 h ago
- Context
- 8.19K tokens
- T2 · 3 h ago
- Released
- 11 May 2026
- T2 · 25 min ago
- License
- apache-2.0
- T2 · 2 h ago
Specification
- Release date
- 11 May 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 25 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- HYV3ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 30.1B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Active parameters
- 3B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Context window
- 8.19K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 4.1K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- 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
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- File size
- 60.1 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- tencent/Hy-MT2-30B-A3B
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Pipeline tag
- translation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 22,074
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 25 min agomedium
- Likes
- 497
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 25 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-07-21T12:22:53+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 232,056
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 25 min agomedium
- Model type
- hy_v3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- tencent/hy-mt2-30b-a3b
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Supported parameters
- max_completion_tokens, max_tokens, response_format, stop, structured_outputs, temperature
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- 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
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
30
Source tiers
T230
Freshest observation
25 min ago
Conflicts
None
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
- 8.19K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 4.1K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- 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
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRoutertencent/hy-mt2-30b-a3b | $0.074 | $0.295 | — | — | 8.19K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 17.8 GB | Yes |
| Apple M3 Ultra | 4bit | — | 17.8 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 17.8 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 17.8 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 17.8 GB | Yes |
| Apple M2 Ultra | 4bit | — | 17.8 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 17.8 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 17.8 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 17.8 GB | Yes |
| Apple M1 Ultra | 4bit | — | 17.8 GB | Yes |
| Apple M3 Max | 4bit | — | 17.8 GB | Yes |
| Apple M4 Max | 4bit | — | 17.8 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 17.8 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 17.8 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 17.8 GB | Yes |
| Apple M2 Max | 4bit | — | 17.8 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 17.8 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 17.8 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 17.8 GB | Yes |
| Apple M1 Max | 4bit | — | 17.8 GB | Yes |
| Apple M4 Pro | 4bit | — | 17.8 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 17.8 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 17.8 GB | Yes |
| Apple M3 Pro | 4bit | — | 17.8 GB | Yes |
| Apple M1 Pro | 4bit | — | 17.8 GB | Yes |
| Apple M2 Pro | 4bit | — | 17.8 GB | Yes |
| Apple M4 | 4bit | — | 17.8 GB | Yes |
| iMac (Apple M4) | 4bit | — | 17.8 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 17.8 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 17.8 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 17.8 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 17.8 GB | Yes |
| Apple M2 | 4bit | — | 17.8 GB | Yes |
| Apple M3 | 4bit | — | 17.8 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 17.8 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 17.8 GB | Yes |
| Apple M1 | 4bit | — | 17.8 GB | No |
No lineage recorded
Papers 1
- arXiv:2605.22064Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Hugging Face repo
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| tencent/Hy-MT2-30B-A3B | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
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 →
Hy-MT2-30B-A3B: release date changed from 2026-05-11 to 2026-08-20
Release date11 May 2026→20 Aug 2026openrouterHy-MT2-30B-A3B: release date changed from 2026-08-20 to 2026-05-11
Release date20 Aug 2026→11 May 2026huggingfaceOpenRouter lists Hy-MT2-30B-A3B at $0.074 in / $0.295 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/tencent/Hy-MT2-30B-A3B | model_page | T2· Quality secondary | 25 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=tencent&p=0&sort=downloads | listing | T2· Quality secondary | 1 h ago | 3 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/tencent/Hy-MT2-30B-A3B/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.