Qwen3.5 2B
Qwen
Code Multilingual Thinking Tool Calls Vision
Qwen3.5 2B is a lightweight model from Alibaba's Qwen 3.5 family built on the Gated Delta Networks hybrid architecture with 2.27 billion parameters, balancing capability and efficiency for edge deployment. It is natively multimodal, processing text, images, and video, with built-in thinking capabilities for chain-of-thought reasoning. The model supports a 262K context window and covers over 201 languages, handling code generation and multilingual tasks with ease. Released under the Apache 2.0 license, it runs in roughly 2 GB of VRAM at Q4, making it practical for self-hosted deployment on modest hardware.
Hardware Configuration
Optional — for precise deployment recommendations
| Quantization | Quality | Size | Fit |
|---|---|---|---|
| Q8_0 | High | 1.87 GB | — |
| Q8_K_XL | High | 2.64 GB | — |
| Q6_K | High | 1.47 GB | — |
| Q6_K_XL | High | 1.74 GB | — |
| Q5_K_M | Medium | 1.34 GB | — |
| Q5_K_S | Medium | 1.29 GB | — |
| Q5_K_XL | Medium | 1.37 GB | — |
| Q4_K_M | Medium | 1.19 GB | — |
| Q4_K_S | Medium | 1.13 GB | — |
| Q4_K_XL | Medium | 1.25 GB | — |
| Q4_0 | Medium | 1.13 GB | — |
| Q4_1 | Medium | 1.2 GB | — |
| Q3_K_M | Low | 1.03 GB | — |
| Q3_K_S | Low | 0.96 GB | — |
| Q3_K_XL | Low | 1.08 GB | — |
| Q2_K_XL | Low | 0.9 GB | — |
Last updated: March 13, 2026