Skip to main content

​
About the Provider

Alibaba Cloud is the cloud computing arm of Alibaba Group and the creator of the Qwen model family. Through its open-source initiative, Alibaba has released state-of-the-art language and multimodal models under permissive licenses, enabling developers and enterprises to build powerful AI applications across diverse domains and languages.

​
Model Quickstart

This section helps you quickly get started with the Qwen/Qwen3.5-27B model on the Qubrid AI inferencing platform. To use this model, you need:
  • A valid Qubrid API key
  • Access to the Qubrid inference API
  • Basic knowledge of making API requests in your preferred language
Once authenticated with your API key, you can send inference requests to the Qwen/Qwen3.5-27B model and receive responses based on your input prompts. Below are example placeholders showing how the model can be accessed using different programming environments.
You can choose the one that best fits your workflow. 
from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
    model="Qwen/Qwen3.5-27B",
    messages=[
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image? Describe the main elements."
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
            }
          }
        ]
      }
    ],
    max_tokens=8192,
    temperature=0.6,
    top_p=0.95,
    stream=True
)

# If stream = False comment this out
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

​
Model Overview

Qwen3.5-27B is a dense (non-MoE) transformer model and the only full-weight model in the Qwen3.5 Medium Series.
  • Released February 24, 2026, it achieves 72.4% on SWE-bench Verified — matching GPT-5 mini — despite having just 27B parameters.
  • It supports native multimodal input (text + images + video) via early fusion, runs on a 22GB Mac M-series device, and natively extends to 1M token contexts.

​
Model at a Glance

FeatureDetails
Model IDQwen/Qwen3.5-27B
ProviderAlibaba Cloud (Qwen Team)
ArchitectureDense Transformer with Gated DeltaNet hybrid attention (linear + full attention, 3:1 ratio), early fusion multimodal vision encoder
Model Size27B (dense)
Context Length256K Tokens (up to 1M)
Release DateFebruary 24, 2026
LicenseApache 2.0
Training DataTrillions of multimodal tokens (text, image, video) across 201 languages; RL post-training for reasoning and agentic tasks

​
When to use?

You should consider using Qwen3.5-27B if:
  • You need local deployment on consumer hardware (22GB+ RAM)
  • Your application involves agentic coding and software development
  • Your use case requires multimodal chat across text, images, and video
  • You need complex reasoning and analysis without MoE routing complexity
  • Your workflow involves long-context document processing
  • You want to fine-tune a dense model for specialized domains

​
Inference Parameters

Parameter NameTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output.
Temperaturenumber0.6Use 0.6 for non-thinking tasks, 1.0 for thinking/reasoning tasks.
Max Tokensnumber8192Maximum number of tokens to generate.
Top Pnumber0.95Nucleus sampling parameter.
Top Knumber20Limits token sampling to top-k candidates.
Enable ThinkingbooleanfalseToggle chain-of-thought reasoning mode. Set temperature=1.0 when enabled.

​
Key Features

  • 72.4% SWE-bench Verified: Matches GPT-5 mini on software engineering benchmarks at just 27B parameters.
  • Dense Architecture: No MoE routing overhead — simpler deployment and more predictable per-token compute.
  • Native Multimodal: Text, image, and video via early fusion — no separate vision encoder.
  • 1M Token Context: 256K natively, extensible to 1M tokens for long-horizon document processing.
  • Consumer Hardware Friendly: Runs on a 22GB Mac M-series or equivalent consumer GPU.
  • Fine-tuning Ready: Dense architecture makes it straightforward to fine-tune for specialized domains.
  • Apache 2.0 License: Fully open source with full commercial freedom.

​
Summary

Qwen3.5-27B is the dense flagship of the Qwen3.5 Medium Series, optimized for coding, reasoning, and local deployment.
  • It uses a dense Transformer with Gated DeltaNet hybrid attention and an early fusion multimodal vision encoder.
  • It matches GPT-5 mini on SWE-bench Verified at 27B parameters, making it highly efficient for its capability tier.
  • The model supports 256K native context (up to 1M), optional thinking mode, and 201 languages.
  • Licensed under Apache 2.0 for full commercial use, deployable on 22GB consumer hardware.