Qwen 3.5 2B
by Alibaba · qwen-3.5 family
2B
parameters
text-generation code-generation reasoning multilingual vision
Qwen 3.5 2B is a compact multimodal model that punches above its weight class. It handles text and vision tasks with 256K context across 201 languages. Needs about 3 GB of VRAM at Q4, making it a strong choice for laptops and entry-level hardware where you want more capability than a sub-1B model.
Quick Start with Ollama
ollama run 2b-q4_K_M | Creator | Alibaba |
| Parameters | 2B |
| Architecture | transformer-decoder |
| Context | 256K tokens |
| Released | Mar 2, 2026 |
| License | Apache 2.0 |
| Ollama | qwen3.5:2b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 2.7 GB | 3 GB | | 2b-q4_K_M |
| Q8_0 | 4 GB | 4.5 GB | | 2b-q8_0 |
Compatible Hardware
Q4_K_M requires 3 GB VRAM