Qwen 3.5 35B-A3B
Alibaba
Sparse MoE Qwen 3.5 with 35B total / 3B active parameters. 256 experts with 8+1 active per token. Efficient inference with quality approaching much larger models.
Text Generation Local Qwen Family v3.5
Parameters
35B
params
Context Window
262K
tokens
Max Output
66K
tokens
Input Price
-
per 1M tokens
Output Price
-
per 1M tokens
Qwen Family Timeline 13 versions
Qwen 3.5 35B-A3B Current local
Feb 2026
Capabilities
👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support
Local Model Specs
Quantization
Q4_K_M
Architecture
Sparse MoE (256 experts, 8+1 active, 3B active)
Runtime
Ollama / llama.cpp
Disk Size
24 GB
Details
- Release Date
- February 24, 2026
- Knowledge Cutoff
- -
- Source
- Local
- License
- Apache 2.0
- Model ID
- qwen3.5-35b-a3b
Last updated: March 13, 2026