Qwen3.5-122B-A10B
Active Parameters
122B
Context Length
262K
Modality
Multimodal
Auxiliary Parameters
450M
Architecture
Mixture of Experts
KV Cache Rate
96 KB/tok
License
Apache 2.0
Release Date
24 Feb 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.26 · Output: $2.08
Hardware & System Requirements
Precision
Context
Workload Memory: 249.12 GB
FP16 · 8K context
Base Weights: 245.87 GB
KV Cache: 0.75 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
8x NVIDIA H100 80GB
249.1 / 576.0 GB usable · TP 8
Determine requirements for your specific workload:
Open in VRAM Calculator
Runtime requirements
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.57.0.dev0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Architecture Diagram
Evaluation Benchmarks
Rank
#101
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.867 | 6 |
Graduate-Level QA | 0.866 | 38 |
Agentic Index | auto 0.08 | 97 |
Web Development | 1360 | 98 |
Coding Index | 0.43 | 103 |
General Text | 1416 | 108 |
Intelligence Index | auto 0.16 Standard 0.18 | 203 187 |
Rankings
Overall Rank
#101
Coding Rank
#109
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.
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
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Auxiliary Parameters
450M
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
FFN Intermediate Size (per Expert)
1,024
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.