Qwen 3.5 27B
by Alibaba · qwen-3.5 family
27B
parameters
text-generation code-generation reasoning multilingual vision tool-use math creative-writing summarization
Qwen 3.5 27B is a powerful dense multimodal model that excels across text, vision, coding, and agentic tasks. With 256K context and 201-language support, it's one of the most versatile models in its size class. At Q4 it needs about 19 GB VRAM, fitting well on a RTX 3090/4090 or a Mac with 24 GB+ unified memory.
Quick Start with Ollama
ollama run 27b-q4_K_M | Creator | Alibaba |
| Parameters | 27B |
| Architecture | transformer-decoder |
| Context | 256K tokens |
| Released | Mar 15, 2026 |
| License | Apache 2.0 |
| Ollama | qwen3.5:27b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 17 GB | 19 GB | | 27b-q4_K_M |
| Q8_0 | 30 GB | 33 GB | | 27b-q8_0 |
Compatible Hardware
Q4_K_M requires 19 GB VRAM