Active Parameters
235B
Context Length
131K
Modality
Text
Architecture
Mixture of Experts
KV Cache Rate
400 KB/tok
License
Apache 2.0
Release Date
29 Apr 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.26 · Output: $1.06
Precision
Context
Workload Memory: 484.32 GB
FP16 · 8K context
Base Weights: 478.70 GB
KV Cache: 3.13 GB
Runtime & Graphs: 2.50 GB
8x NVIDIA H100 80GB
484.3 / 576.0 GB usable · TP 8
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.51.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#150
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.682 | 47 |
Graduate-Level QA | 0.775 | 71 |
General Text | 1422 | 101 |
Agentic Index | 0.01 | 108 |
Coding Index | 0.22 | 129 |
Intelligence Index | 0.12 | 239 |
General Knowledge Reference | 0.878 | 6 |
Coding Archived | 0.60 | 10 |
Overall Rank
#150
Coding Rank
#140
Qwen3-235B-A22B is Alibaba Cloud's flagship open-source Mixture-of-Experts model activating 22B parameters for advanced computational linguistics and STEM problem solving. It combines dynamic thinking modes with sparse MoE efficiency across 119 languages.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
128
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
1,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
10,240
Number of Layers
100
FFN Intermediate Size (Dense)
1,536
Tokenizer
Vocabulary Size
151,936
Mixture of Experts
Total Expert Parameters
22.0B
Number of Experts
128
Active Experts
8
FFN Intermediate Size (per Expert)
1,536
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.