Qwen3.5-122B-A10B
Active Parameters
122B
Context Length
262K
Modality
Multimodal
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
24 Feb 2026
Knowledge Cutoff
-
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
13x RTX 4090
24GB VRAM
Datacenter
4x NVIDIA A100
80GB VRAM
Apple Silicon
3x Apple M3 Max
128GB VRAM
262,144 tokens
Consumer
15x RTX 4090
24GB VRAM
Datacenter
4x NVIDIA A100
80GB VRAM
Apple Silicon
3x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#83
| Benchmark | Score | Rank |
|---|---|---|
Web Development | 1358 | 64 |
General Text | 1417 | 80 |
Rankings
Overall Rank
#83
Coding Rank
#66
About Qwen3.5-122B-A10B
Qwen3.5-122B-A10B is Alibaba Cloud's mid-tier multimodal foundation model, released February 2026. With 122B total parameters and 10B activated through a Mixture-of-Experts architecture (256 experts), it balances high performance with computational efficiency. It achieves strong scores on MMLU-Pro (86.1%), GPQA Diamond (85.5%), SWE-bench Verified (72.4%), and Terminal-Bench 2.0 (41.6%). Features unified vision-language capabilities, 262k native context (extensible to 1M), and excels across reasoning, coding, agentic workflows, and multilingual tasks.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
32
Key-Value Heads
2
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
10,000,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
3,072
Number of Layers
48
FFN Intermediate Size (Dense)
1,024
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,320
Mixture of Experts
Total Expert Parameters
10.0B
Number of Experts
256
Active Experts
9
Shared Experts
-
FFN Intermediate Size (per Expert)
1,024
Dense Layers Before MoE
-
About Qwen 3.5
Qwen 3.5 is Alibaba Cloud's latest-generation foundation model family, released February 2026. It represents a significant leap forward, integrating breakthroughs in multimodal learning (unified vision-language foundation), efficient hybrid architecture (Gated Delta Networks with sparse Mixture-of-Experts), scalable reinforcement learning across million-agent environments, and global linguistic coverage spanning 201 languages. Available under Apache 2.0 license with open weights.