Overview
Qwen3.6-27B is a 27.8B-parameter dense model from Qwen, the model team at Alibaba Cloud. The Hugging Face tags mark it as image-text-to-text and part of the qwen3_5 line, so it is natively multimodal: it reads images and text in one pass rather than bolting vision on afterward. It ships with a 262,144-token context window, and Qwen documents extending that toward roughly a million tokens with the right serving setup.
Because it is a dense model instead of a Mixture-of-Experts router, it loads and runs without MoE routing overhead, which makes it predictable on a single GPU. With Atomic Chat you can run all 27.8B parameters on your own machine, fully offline. Prompts, code, and documents stay on your hardware, and nothing is sent to an API.
What it is good at
The capability set covers reasoning, code, vision, tool calling, and embeddings, so a single local copy handles a wide range of work:
- Agentic coding — Qwen reports Qwen3.6-27B scoring 77.2 on SWE-bench Verified and 59.3 on Terminal-Bench 2.0, ahead of the older Qwen3.5-397B-A17B flagship, which makes it suited to repository-level edits and frontend work.
- Vision and document understanding — the built-in vision encoder reads screenshots, scanned pages with OCR, and long video, so you can ask questions about an image or a PDF without an external service.
- Tool calling with thinking — the model supports structured tool calls and a thinking mode, letting it plan multi-step tasks and invoke functions inside an agent loop.
Running it locally
At 27.8B parameters, a 16 GB GPU such as an RTX 4080 or 16 GB of Apple unified memory runs the Q4_K_M quantization at around 16.8 GB. A 24 GB card like the RTX 3090 or 4090 gives headroom for Q6_K and longer slices of the 262,144-token context. Pull the original weights from Hugging Face:
huggingface-cli download Qwen/Qwen3.6-27B
From there you can serve it with Transformers or vLLM, load a GGUF build in LM Studio, or use the one-click download in Atomic Chat to get it running without touching the terminal.
License
Qwen3.6-27B is released under the Apache-2.0 license. That permits commercial use, modification, redistribution, and private deployment with no royalties, so you can build products on top of the model and run it on your own hardware without a usage fee.