Qwen3.5 0.8B
Qwen
Code Multilingual Thinking Tool Calls Vision
Qwen3.5 0.8B is the smallest model in Alibaba's Qwen 3.5 family, built on the Gated Delta Networks hybrid architecture with 0.87 billion parameters, purpose-built for phones, edge devices, and ultra-constrained environments. 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. Released under the Apache 2.0 license, it quantizes down to under 1 GB of VRAM at Q4, making it ideal for classification and simple tasks in self-hosted deployment scenarios.
Hardware Configuration
Optional — for precise deployment recommendations
| Quantization | Quality | Size | Fit |
|---|---|---|---|
| Q8_0 | High | 0.76 GB | — |
| Q8_K_XL | High | 1.1 GB | — |
| Q6_K | High | 0.6 GB | — |
| Q6_K_XL | High | 0.72 GB | — |
| Q5_K_M | Medium | 0.55 GB | — |
| Q5_K_S | Medium | 0.53 GB | — |
| Q5_K_XL | Medium | 0.56 GB | — |
| Q4_K_M | Medium | 0.5 GB | — |
| Q4_K_S | Medium | 0.47 GB | — |
| Q4_K_XL | Medium | 0.52 GB | — |
| Q4_0 | Medium | 0.47 GB | — |
| Q4_1 | Medium | 0.5 GB | — |
| Q3_K_M | Low | 0.44 GB | — |
| Q3_K_S | Low | 0.41 GB | — |
| Q3_K_XL | Low | 0.46 GB | — |
| Q2_K_XL | Low | 0.39 GB | — |
Last updated: March 13, 2026