Hy-MT2-7B
Tencenthuggingface.co/tencent/Hy-MT2-7B
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.
Updated 18 min ago · first seen 11 Sept 2026
model_01M294WVQWF9JECPA522GVTFZA
- Parameters
- 8.03B
- T2 · 3 h ago
- Context
- 8.19K tokens
- T2 · 3 h ago
- Released
- 11 May 2026
- T2 · 18 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 18 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
- HunYuanDenseV1ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 8.03B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 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
- 16.1 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- tencent/Hy-MT2-7B
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
- 13,357
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 18 min agomedium
- Likes
- 211
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 18 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-05-26T09:05:54+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
- 93,190
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 18 min agomedium
- Model type
- hunyuan_v1_dense
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- tencent/hy-mt2-7b
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, hunyuan_v1_dense, 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
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
29
Source tiers
T229
Freshest observation
18 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-mt2-7b | $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 | 5.1 GB | Yes |
| Apple M3 Ultra | 4bit | — | 5.1 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 5.1 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 5.1 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 5.1 GB | Yes |
| Apple M2 Ultra | 4bit | — | 5.1 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 5.1 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 5.1 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 5.1 GB | Yes |
| Apple M1 Ultra | 4bit | — | 5.1 GB | Yes |
| Apple M3 Max | 4bit | — | 5.1 GB | Yes |
| Apple M4 Max | 4bit | — | 5.1 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 5.1 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 5.1 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 5.1 GB | Yes |
| Apple M2 Max | 4bit | — | 5.1 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 5.1 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 5.1 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 5.1 GB | Yes |
| Apple M1 Max | 4bit | — | 5.1 GB | Yes |
| Apple M4 Pro | 4bit | — | 5.1 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 5.1 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 5.1 GB | Yes |
| Apple M3 Pro | 4bit | — | 5.1 GB | Yes |
| Apple M1 Pro | 4bit | — | 5.1 GB | Yes |
| Apple M2 Pro | 4bit | — | 5.1 GB | Yes |
| Apple M4 | 4bit | — | 5.1 GB | Yes |
| iMac (Apple M4) | 4bit | — | 5.1 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 5.1 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 5.1 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 5.1 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 5.1 GB | Yes |
| Apple M2 | 4bit | — | 5.1 GB | Yes |
| Apple M3 | 4bit | — | 5.1 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 5.1 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 5.1 GB | Yes |
| Apple M1 | 4bit | — | 5.1 GB | Yes |
Ancestors 0
None recorded.
Descendants 0
None 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 · Release date
Release daterelease_date4
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 11 May 2026 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 19 Aug 2026 | → | superseded | OpenRouter public model & pricing listingT2 | medium | deterministic |
| 11 May 2026 | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 19 Aug 2026 | → | superseded | 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-MT2-7B: release date changed from 2026-05-11 to 2026-08-19
Release date11 May 2026→19 Aug 2026openrouterHy-MT2-7B: release date changed from 2026-08-19 to 2026-05-11
Release date19 Aug 2026→11 May 2026huggingfaceOpenRouter lists Hy-MT2-7B 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-MT2-7B | model_page | T2· Quality secondary | 18 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/tencent/Hy-MT2-7B-GGUF | model_page | T2· Quality secondary | 18 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=tencent&p=0&sort=downloads | listing | T2· Quality secondary | 53 min 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-MT2-7B/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.