Hy-MT2 30B A3B
Active Parameters
30B
Context Length
8K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
11 May 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.07 · Output: $0.29
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
8,192 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for Hy-MT2 30B A3B available.
Rankings
Overall Rank
-
Coding Rank
-
About Hy-MT2 30B A3B
Hy-MT2 30B A3B is Tencent's flagship mixture-of-experts translation model with 3B active parameters out of 30B total. It delivers high-accuracy translation across 33 language pairs with advanced support for context-aware and glossary-based tasks.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
4
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
11,158,840
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
No
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
2,048
Number of Layers
48
FFN Intermediate Size (Dense)
6,912
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
120,832
Mixture of Experts
Total Expert Parameters
3.0B
Number of Experts
128
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
768
Dense Layers Before MoE
1
Resources
About Hunyuan
Tencent Hunyuan large language models with various capabilities.