runlocal.devCheck My GPU →

Qwen 3.6 27B

Qwen

Alibaba's 27B dense multimodal model. SWE-bench Verified 77.2 — surpasses Qwen 3.5 397B on coding. Native image/video/text input; compatible with Claude Code and Qwen Code tooling.

Provider

Alibaba

Parameters

27B

Context

131.072K

Released

2026-04-22

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
Q8_027.5 GB30 GB5 GPUs
Q4_K_M15.5 GB17 GB9 GPUs
Q4_014.8 GB16 GB9 GPUs
Q2_K9.5 GB11 GB18 GPUs

Install with Ollama

Run in terminal:

ollama pull qwen3.6:27b

Minimum 11GB VRAM required. Install Ollama from ollama.com

Benchmark Scores

mmlu85%
humaneval88.5%

Scores are approximate and may vary by quantization level.

Compatible GPUs (18)

HuggingFace

Qwen/Qwen3.6-27B-Instruct

View on HF →