Skip to content

Qwen 3.5 27B

Apache 2.0

Alibaba · 27B · transformer-decoder

2026-03-15262K context27B params

Use Cases

chatcodereasoningmultilingualvisiontoolsmathwritingsummary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec419.0 GBGood
Q8_0833.0 GBExcellent

About this model

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.