Qwen/Qwen3.6-27B

Preview

qwen/qwen3.6-27b

Try it in Playground

TOKEN SPEED

~500 tps

Powered bygroq

INPUT

Text, images

OUTPUT

Text

CAPABILITIES

Tool Use, JSON Object Mode, Reasoning, Vision

Alibaba Cloud

Model card

Qwen 3.6 27B is a 27-billion-parameter multimodal model from Alibaba's Qwen series, delivering flagship-level agentic coding and reasoning that rivals models many times its size. It accepts both image and text inputs for visual understanding tasks such as image analysis, OCR, and visual question answering, and supports seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within a single model, with a long context window and strong multilingual support.

---

PRICING

Input

$0.60

1.7M / $1

Output

$3.00

333,333 / $1

---

LIMITS

CONTEXT WINDOW

131,072

---

MAX OUTPUT TOKENS

32,768

---

MAX FILE SIZE

20 MB

---

MAX INPUT IMAGES

3

---

QUANTIZATION

This uses Groq's TruePoint Numerics, which reduces precision only in areas that don't affect accuracy, preserving quality while delivering significant speedup over traditional approaches. Learn more here.

Key Technical Specifications

Best Practices

• Mode Selection: use thinking mode (reasoning_effort="default") for complex reasoning, math, and coding, and non-thinking mode (reasoning_effort="none") for efficient, general-purpose dialogue.
• Thinking Mode (general): temperature=1.0, top_p=0.95, top_k=20, min_p=0. For precise coding tasks, lower the temperature to 0.6.
• Non-thinking Mode: temperature=0.7, top_p=0.80, top_k=20, min_p=0, presence_penalty=1.5.
• Math Problems: include 'Please reason step by step, and put your final answer within \boxed{}' in the prompt.
• History Management: in multi-turn conversations, only include final outputs without thinking content.
• Reasoning Format: set reasoning_format to hidden to return only the final answer, or parsed to include the reasoning in a separate field.
• Use the full 131K context window for repository-scale code and multi-document workflows.

Get Started with Qwen 3.6 27B

Experience state-of-the-art reasoning and agentic coding with Qwen 3.6 27B at Groq speed:

pip install groq

from groq import Groq
client = Groq()
completion = client.chat.completions.create(
    model="qwen/qwen3.6-27b",
    messages=[
        {
            "role": "user",
            "content": "Explain why fast inference is critical for reasoning models"
        }
    ]
)
print(completion.choices[0].message.content)