Qwen3.6-27B | NVIDIA NeMo AutoModel

Qwen3.6 is Alibaba Cloud’s unified vision-language model generation following Qwen3.5. NeMo AutoModel supports both the dense 27B checkpoint and the 35B-A3B MoE checkpoint.

Fine-Tune Qwen3.6-27B

uv run automodel --nproc-per-node=8 examples/vlm_finetune/qwen3_5/qwen3_6_27b.yaml

Install the vlm-media extra before running these recipes. See the Installation Guide and VLM Fine-Tuning Guide.

Model Reference

Model Architecture

Property	Value
Task	Image-Text-to-Text
Architecture	`Qwen3_5ForConditionalGeneration`, `Qwen3_5MoeForConditionalGeneration`
Parameters	27B dense; 35B total / 3B active MoE
HF Org	Qwen

Example Models and Recipes

Model	Recipe	Description
`Qwen/Qwen3.6-27B`	qwen3_6_27b.yaml	Full SFT on MedPix-VQA
`Qwen/Qwen3.6-27B`	qwen3_6_27b_lora.yaml	LoRA on MedPix-VQA
`Qwen/Qwen3.6-35B-A3B`	qwen3_6_35b.yaml	Full SFT on MedPix-VQA
`Qwen/Qwen3.6-35B-A3B`	qwen3_6_35b_lora.yaml	LoRA on MedPix-VQA