Qwen3.5-9B
Parameters
9B
Context Length
262K
Modality
Multimodal
Auxiliary Parameters
450M
Architecture
Dense
KV Cache Rate
128 KB/tok
License
Apache 2.0
Release Date
24 Feb 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.14 · Output: $0.20
Hardware Sizing
Precision
Context
Workload Memory: 7.69 GB
INT4 · 8K context
Base Weights: 4.19 GB
KV Cache: 1.00 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
7.7 / 21.6 GB usable
1x RTX 3060 12GB
7.7 / 10.8 GB usable
Apple M4 24GB
7.7 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#124
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.825 | 21 |
Graduate-Level QA | 0.817 | 59 |
Agentic Index | auto 0.01 | 111 |
Coding Index | 0.23 | 126 |
Intelligence Index | auto 0.11 Standard 0.13 | 229 207 |
Rankings
Overall Rank
#124
Coding Rank
#131
About Qwen3.5-9B
Qwen3.5-9B is Alibaba Cloud's efficient multimodal foundation model with 9B parameters, released February 2026. It uses a hybrid architecture combining Gated Delta Networks and Gated Attention in an 8×(3×DeltaNet→FFN→1×Attention→FFN) pattern. It achieves strong scores on MMLU-Pro (82.5%), GPQA Diamond (81.7%), HMMT benchmarks (90%/90%), and LiveCodeBench v6 (82.7%). Features unified vision-language capabilities, 262k native context (extensible to 1M), multi-token prediction training, and excels in multimodal reasoning, coding, agents, and multilingual tasks across 201 languages.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
16
Key-Value Heads
4
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
Auxiliary Parameters
450M
Hidden Dimension Size
4,096
Number of Layers
32
FFN Intermediate Size (Dense)
12,288
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,320
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.