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/Qwen3.5-122B-A10B 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/Qwen3.5-122B-A10B 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/Qwen3.5-122B-A10B",
    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=16384,
    temperature=1,
    top_p=0.95,
    stream=True,
    presence_penalty=1.5
)

# 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

Qwen3.5-122B-A10B is the most powerful open-source model in the Qwen3.5 Medium Series.
  • With 122B total parameters and 10B active per token across a 48-layer hybrid architecture, it delivers the strongest knowledge, vision, and function-calling performance in the medium class.
  • It scores 86.6% on GPQA Diamond (beating GPT-5 mini’s 82.8%), 72.2% on BFCL-V4 tool calling (vs GPT-5 mini’s 55.5%), 92.1% on OCRBench, and 83.9% on MMMU.
  • Supports text, image, and video input natively via early fusion.

​
Model at a Glance

FeatureDetails
Model IDQwen/Qwen3.5-122B-A10B
ProviderAlibaba Cloud (Qwen Team)
ArchitectureHybrid Gated DeltaNet + Sparse MoE Transformer — 48 layers, 16 DeltaNet-attention cycles (3:1 ratio), 256 experts (10B active per token), early fusion multimodal vision encoder, MTP speculative decoding
Model Size122B Total / 10B Active
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 Qwen3.5-122B-A10B if:
  • You need advanced multimodal reasoning across text, image, and video
  • Your application requires enterprise-grade document understanding and OCR
  • You are building complex agentic workflows with function calling
  • You need long-horizon planning and analysis with 256K context
  • Your use case involves GUI automation
  • You need scientific and research-grade problem solving
  • Your application requires RAG over massive document repositories

​
Inference Parameters

Parameter NameTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output.
Temperaturenumber1Recommended 1.0 for thinking mode. Use 0.6–0.7 for non-thinking tasks.
Max Tokensnumber16384Maximum tokens to generate. Thinking mode may require higher values.
Top Pnumber0.95Nucleus sampling parameter.
Top Knumber20Limits token sampling to top-k candidates.
Presence Penaltynumber1.5Reduces repetition in longer outputs. Recommended 1.5 for this model.
Enable ThinkingbooleantrueToggle chain-of-thought reasoning. Enables deep problem solving at the cost of higher latency.

​
Key Features

  • 86.6% GPQA Diamond: Beats GPT-5 mini (82.8%) by 4 points on graduate-level reasoning.
  • 72.2% BFCL-V4 Function Calling: 30% ahead of GPT-5 mini (55.5%) on tool calling benchmarks.
  • 92.1% OCRBench: Best open-weight document model with 89.8% OmniDocBench.
  • 70.4% ScreenSpot Pro: 2× Claude Sonnet 4.5 (36.2%) on GUI automation tasks.
  • Native Multimodal: Text, image, and video via early fusion — no separate vision encoder.
  • MTP Speculative Decoding: Enhanced throughput via Multi-Token Prediction.
  • Apache 2.0 License: Full commercial freedom with open weights.

​
Summary

Qwen3.5-122B-A10B is the most powerful model in the Qwen3.5 Medium Series for vision, reasoning, and tool calling.
  • It uses a 48-layer hybrid Gated DeltaNet + Sparse MoE architecture with 122B total and 10B active parameters.
  • It outperforms GPT-5 mini on GPQA Diamond, BFCL-V4, and GUI automation benchmarks.
  • The model supports 256K native context, configurable thinking mode, and 201 languages.
  • Licensed under Apache 2.0 for full commercial use.