Qwen3.5-0.8B

[!Note] This repository contains model weights and configuration files for the post-trained model in the ONNX format.

These artifacts are compatible with Hugging Face Transformers,js, ONNX Runtime, etc.

In light of its parameter scale, the intended use cases are prototyping, task-specific fine-tuning, and other research or development purposes.

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.

Qwen3.5 Highlights

Qwen3.5 features the following enhancement:

• Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.

• Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.

• Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.

• Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.

• Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

For more details, please refer to our blog post Qwen3.5.

Model Overview

• Type: Causal Language Model with Vision Encoder
• Training Stage: Pre-training & Post-training
• Language Model
  • Number of Parameters: 0.8B
  • Hidden Dimension: 1024
  • Token Embedding: 248320 (Padded)
  • Number of Layers: 24
  • Hidden Layout: 6 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
  • Gated DeltaNet:
    • Number of Linear Attention Heads: 16 for V and 16 for QK
    • Head Dimension: 128
  • Gated Attention:
    • Number of Attention Heads: 8 for Q and 2 for KV
    • Head Dimension: 256
    • Rotary Position Embedding Dimension: 64
  • Feed Forward Network:
    • Intermediate Dimension: 3584
  • LM Output: 248320 (Tied to token embedding)
  • MTP: trained with multi-steps
• Context Length: 262,144 natively

Benchmark Results

Language

Vision Language

Quickstart

[!Important] Qwen3.5 models support both non-thinking and thinking mode. Qwen3.5-0.8B operates in non-thinking mode by default. To enable thinking, refer to the examples here.

For streamlined integration, we recommend using Qwen3.5 via APIs. Below is a guide to use Qwen3.5 via OpenAI-compatible API.

Transformers.js

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers@next

You can then use the model like this:

import {
  AutoProcessor,
  Qwen3_5ForConditionalGeneration,
  RawImage,
  TextStreamer,
} from "@huggingface/transformers";

const model_id = "onnx-community/Qwen3.5-0.8B-ONNX";
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await Qwen3_5ForConditionalGeneration.from_pretrained(model_id, {
  dtype: {
    embed_tokens: "q4",
    vision_encoder: "fp16",
    decoder_model_merged: "q4",
  },
  device: "webgpu",
});

// Prepare inputs
const url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg";
const image = await (await RawImage.read(url)).resize(448, 448);
const conversation = [
  {
    role: "user",
    content: [
      { type: "image" },
      { type: "text", text: "Describe this image." },
    ],
  },
];
const text = processor.apply_chat_template(conversation, {
  add_generation_prompt: true,
});
const inputs = await processor(text, image);

const outputs = await model.generate({
  ...inputs,
  max_new_tokens: 512,
  streamer: new TextStreamer(processor.tokenizer, {
    skip_prompt: true,
    skip_special_tokens: false,
  }),
});

// Decode output
const decoded = processor.batch_decode(
  outputs.slice(null, [inputs.input_ids.dims.at(-1), null]),
  {
    skip_special_tokens: true,
  },
);
console.log(decoded[0]);

Best Practices

To achieve optimal performance, we recommend the following settings:

1. Sampling Parameters:

   • We suggest using the following sets of sampling parameters depending on the mode and task type:

     • Non-thinking mode for text tasks:
       temperature=1.0, top_p=1.00, top_k=20, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
     • Non-thinking mode for VL tasks:
       temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
     • Thinking mode for text tasks:
       temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
     • Thinking mode for VL or precise coding (e.g., WebDev) tasks:
       temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

   • For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.

2. Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 81,920 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.

3. Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.

   • Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
   • Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g., "answer": "C"."

4. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.

5. Long Video Understanding: To optimize inference efficiency for plain text and images, the size parameter in the released video_preprocessor_config.json is conservatively configured. It is recommended to set the longest_edge parameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,

   {"longest_edge": 469762048, "shortest_edge": 4096}
   

   Alternatively, override the default values via engine startup parameters. For implementation details, refer to: vLLM / SGLang.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3.5,
    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
    author = {{Qwen Team}},
    month  = {February},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.5}
}