Qwen3 Next 80B A3B
Active Parameters
80B
Context Length
66K
Modality
Reasoning
Architecture
Mixture of Experts (MoE)
License
Apache-2.0
Release Date
1 Feb 2026
Knowledge Cutoff
Jun 2025
API Pricing (per 1M)
Input: $0.15 · Output: $1.20
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
9x RTX 4090
24GB VRAM
Datacenter
3x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
66,000 tokens
Consumer
9x RTX 4090
24GB VRAM
Datacenter
3x NVIDIA A100
80GB VRAM
Apple Silicon
2x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#110
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.806 | 21 |
Graduate-Level QA | 0.772 | 58 |
General Text | 1399 | 87 |
Agentic Index | 0.02 | 101 |
Coding Index | 0.17 | 118 |
Intelligence Index | auto 0.11 Standard 0.10 | 187 196 |
Rankings
Overall Rank
#110
Coding Rank
#113
About Qwen3 Next 80B A3B
Qwen3-Next-80B-A3B is a sparse Mixture-of-Experts model by Alibaba activating 3B parameters via hybrid Gated DeltaNet linear attention. It delivers ultra-fast sequence modeling and complex mathematical reasoning over an extensible 1M context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
16
Key-Value Heads
2
Attention Head Dimension
256
Position Embedding
Absolute Position Embedding
RoPE Theta
10,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
2,048
Number of Layers
48
FFN Intermediate Size (Dense)
512
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
151,936
Mixture of Experts
Total Expert Parameters
79.0B
Number of Experts
512
Active Experts
10
Shared Experts
-
FFN Intermediate Size (per Expert)
512
Dense Layers Before MoE
-
About Qwen 3
The Alibaba Qwen 3 model family comprises dense and Mixture-of-Experts (MoE) architectures, with parameter counts from 0.6B to 235B. Key innovations include a hybrid reasoning system, offering 'thinking' and 'non-thinking' modes for adaptive processing, and support for extensive context windows, enhancing efficiency and scalability.