DavidAU/Qwen3.5-9B-The-Bradbury-F451-Pro-Writer-Uncensored-Heretic

Qwen3.5-9B-The-Bradbury-F451-Pro-Writer-Uncensored-Heretic

A fine tune via Unsloth using Ray Bradbury's famous "F451" novel as a base to focus the model.

This is also a HERETIC model, trained post "Heretic'ing" -> this model does what you want, no questions asked.

Fully uncensored.

VISION:

• Vision (images) tested -> working with new training.

Benchmarks:

Qwen3.5-9B-The-Bradbury-F451-Pro-Writer-Uncensored-Heretic
           arc   arc/e boolq hswag obkqa piqa  wino
mxfp8      0.590,0.761,0.883,0.697,0.444,0.779,0.684

Qwen3.5-9B
           arc   arc/e boolq hswag obkqa piqa  wino
mxfp8      0.571,0.719,0.895,0.683,0.426,0.770,0.671

---

DE-CENSORING:

Performance

KLD of less than 1 is excellent, zero is perfect.

Metric	This model	Original model (Qwen/Qwen3.5-9B)
KL divergence	0.0793	0 (by definition)
Refusals	6/100	100/100

NOTES:

• Suggest min q4ks (non-imatrix) or IQ3S (imatrix).
• Tested with rep pen of 1 (off).
• Context: 256k (default).

IMPORTANT:

• Other versions in testing.
• Information from Qwen's repo below.
• Video portions of the model were NOT TESTED.

---

Using an "uncensored" (refusals removed) model VS trained "uncensored" model

Usually when you a tell a model to generate horror, swear or x-rated content this is all you have to do to get said content type.

In the case of this model, it will not refuse your request, however it needs to be "pushed" a bit / directed a bit more in SOME CASES.

Although this model will generated x-rated content too, likewise you need to tell it to use "slang" (and include the terms you want) to get it generate the content correctly as the "expected" content level too.

Without these added directive(s), the content can be "bland" by comparison to an "uncensored model" or model trained on uncensored content.

Roughly, the model tries to generate the content but the "default" setting(s) are so "tame" it needs a push to generate at expected graphic, cursing or explicit levels.

Even with minimal direction (ie, use these words to swear: x,y,z), this will be enough to push the model to generate the requested content in the ahh... expected format.

---

Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:

In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;

Set the "Smoothing_factor" to 1.5

: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"

: in text-generation-webui -> parameters -> lower right.

: In Silly Tavern this is called: "Smoothing"

NOTE: For "text-generation-webui"

-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)

Source versions (and config files) of my models are here:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

OTHER OPTIONS:

• Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")

• If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers

This a "Class 1" model:

For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

---

Qwen3.5-9B

This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

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: 9B
  • Hidden Dimension: 4096
  • Token Embedding: 248320 (Padded)
  • Number of Layers: 32
  • Hidden Layout: 8 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
  • Gated DeltaNet:
    • Number of Linear Attention Heads: 32 for V and 16 for QK
    • Head Dimension: 128
  • Gated Attention:
    • Number of Attention Heads: 16 for Q and 4 for KV
    • Head Dimension: 256
    • Rotary Position Embedding Dimension: 64
  • Feed Forward Network:
    • Intermediate Dimension: 12288
  • LM Output: 248320 (Padded)
  • MTP: trained with multi-steps
• Context Length: 262,144 natively and extensible up to 1,010,000 tokens.

Benchmark Results

Language

	GPT-OSS-120B	GPT-OSS-20B	Qwen3-Next-80B-A3B-Thinking	Qwen3-30BA3B-Thinking-2507	Qwen3.5-9B	Qwen3.5-4B
Knowledge & STEM
MMLU-Pro	80.8	74.8	82.7	80.9	82.5	79.1
MMLU-Redux	91.0	87.8	92.5	91.4	91.1	88.8
C-Eval	76.2	71.4	89.7	87.4	88.2	85.1
SuperGPQA	54.6	48.5	60.8	56.8	58.2	52.9
GPQA Diamond	80.1	71.5	77.2	73.4	81.7	76.2
Instruction Following
IFEval	88.9	88.2	88.9	88.9	91.5	89.8
IFBench	69.0	65.1	61.5	51.5	64.5	59.2
MultiChallenge	45.3	40.1	51.3	46.5	54.5	49.0
Long Context
AA-LCR	50.7	30.7	51.7	49.0	63.0	57.0
LongBench v2	48.2	45.6	48.0	44.8	55.2	50.0
Reasoning & Coding
HMMT Feb 25	90.0	76.7	73.7	63.1	83.2	74.0
HMMT Nov 25	90.0	81.8	81.2	73.8	82.9	76.8
LiveCodeBench v6	82.7	74.6	68.7	66.0	65.6	55.8
OJBench	41.5	36.3	29.7	25.1	29.2	24.1
General Agent
BFCL-V4	--	--	49.7	42.4	66.1	50.3
TAU2-Bench	--	--	57.4	41.9	79.1	79.9
VITA-Bench	--	--	29.5	14.1	29.8	22.0
DeepPlanning	--	--	0.4	4.9	18.0	17.6
Multilingualism
MMMLU	78.2	69.7	81.3	78.4	81.2	76.1
MMLU-ProX	74.5	67.3	73.6	69.1	76.3	71.5
NOVA-63	51.1	48.7	53.3	52.5	55.9	54.3
INCLUDE	74.0	65.3	78.3	74.4	75.6	71.0
Global PIQA	84.1	79.8	83.5	80.2	83.2	78.9
PolyMATH	54.0	30.9	62.4	52.6	57.3	51.1
WMT24++	74.4	67.8	57.4	69.3	72.6	66.6
MAXIFE	83.7	80.1	79.9	77.4	83.4	78.0

* TAU2-Bench: we follow the official setup except for the airline domain, where all models are evaluated by applying the fixes proposed in the Claude Opus 4.5 system card.

* MMLU-ProX: we report the averaged accuracy on 29 languages.
* WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL.
* MAXIFE: we report the accuracy on English + multilingual original prompts (totally 23 settings).
* Empty cells (--) indicate scores not yet available or not applicable.

Vision Language

	GPT-5-Nano-2025-08-07	Gemini-2.5-Flash-Lite	Qwen3-VL-30B-A3B	Qwen3.5-9B	Qwen3.5-4B
STEM and Puzzle
MMMU	75.8	73.4	76.0	78.4	77.6
MMMU-Pro	57.2	59.7	63.0	70.1	66.3
MathVision	62.2	52.1	65.7	78.9	74.6
Mathvista(mini)	71.5	72.8	81.9	85.7	85.1
We-Math	62.5	32.1	70.0	75.2	75.4
DynaMath	78.0	69.9	80.1	83.6	83.3
ZEROBench	1.0	1.0	0.0	3.0	3.0
ZEROBench_sub	22.2	19.2	23.7	31.1	26.3
VlmsAreBlind	66.7	68.4	72.5	93.7	92.6
BabyVision	14.4	17.5	18.6	28.6/25.8	16.0/19.1
General VQA
RealWorldQA	71.8	72.2	77.4	80.3	79.5
MMStar	68.6	69.1	75.5	79.7	78.3
MMBenchEN-DEV-v1.1	80.3	82.7	88.9	90.1	89.4
SimpleVQA	46.0	54.1	54.3	51.2	43.4
HallusionBench	58.4	64.5	66.0	69.3	65.0
Text Recognition and Document Understanding
OmniDocBench1.5	55.9	79.4	86.8	87.7	86.2
CharXiv(RQ)	50.1	56.1	56.6	73.0	70.8
MMLongBench-Doc	31.8	46.5	47.4	57.7	54.2
CC-OCR	58.9	72.9	77.8	79.3	76.7
AI2D_TEST	81.9	85.7	86.9	90.2	89.6
OCRBench	75.3	82.5	83.9	89.2	85.0
Spatial Intelligence
ERQA	45.8	44.3	45.3	55.5	54.0
CountBench	80.0	79.2	90.0	97.2	96.3
RefCOCO(avg)	--	--	89.3	89.7	88.1
EmbSpatialBench	74.2	66.1	80.6	83.0	81.3
RefSpatialBench	12.6	11.2	54.2	58.5	54.6
LingoQA	57.0	17.8	62.0	80.4	74.4
Hypersim	--	--	11.4	13.5	12.5
Nuscene	--	--	10.3	11.8	9.9
Video Understanding
VideoMME(w sub.)	71.7	74.6	79.9	84.5	83.5
VideoMME(w/o sub.)	66.2	72.7	73.3	78.4	76.9
VideoMMMU	63.0	69.2	75.0	78.9	74.1
MLVU	69.2	78.5	78.9	84.4	82.8
MVBench	--	--	72.0	74.4	71.2
LVBench	--	60.9	59.2	70.0	66.4
MMVU	63.1	65.3	66.1	67.8	64.9
Visual Agent
ScreenSpot Pro	--	--	60.5	65.2	60.3
OSWorld-Verified	--	--	30.6	41.8	35.6
AndroidWorld	--	--	55.0	57.8	58.6
Tool Calling
TIR-Bench	18.5	21.5	22.5	45.6/31.9	38.9/29.9
V*	68.1	69.6	83.2	90.1/88.5	84.3/86.4
Medical VQA
SLAKE	57.0	65.0	68.8	79.0	76.1
PMC-VQA	37.8	48.8	51.5	57.9	55.5
MedXpertQA-MM	26.7	35.3	35.5	49.9	42.9

* MathVision: our model’s score is evaluated using a fixed prompt, e.g., “Please reason step by step, and put your final answer within \boxed{}.” For other models, we report the higher score between runs with and without the \boxed{} formatting.
* BabyVision: scores reported as "with CI / without CI".
* TIR-Bench and V*: scores reported as "with CI / without CI".
* Empty cells (--) indicate scores not yet available or not applicable.

Quickstart

Qwen3.5 models operate in thinking mode by default, generating thinking content signified by <think>\n...</think>\n\n before producing the final responses. To disable thinking content and obtain direct response, 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.

Serving Qwen3.5

Qwen3.5 can be served via APIs with popular inference frameworks. In the following, we show example commands to launch OpenAI-Compatible API servers for Qwen3.5 models.

Inference efficiency and throughput vary significantly across frameworks. We recommend using the latest framework versions to ensure optimal performance and compatibility. For production workloads or high-throughput scenarios, dedicated serving engines such as SGLang, KTransformers or vLLM are strongly recommended.

The model has a default context length of 262,144 tokens. If you encounter out-of-memory (OOM) errors, consider reducing the context window. However, because Qwen3.5 leverages extended context for complex tasks, we advise maintaining a context length of at least 128K tokens to preserve thinking capabilities.

SGLang

SGLang is a fast serving framework for large language models and vision language models. SGLang from the main branch of the open-source repository is required for Qwen3.5, which can be installed using the following command in a fresh environment:

uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python&egg=sglang[all]'

See its documentation for more details.

The following will create API endpoints at http://localhost:8000/v1:

• Standard Version: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.

  python -m sglang.launch_server --model-path Qwen/Qwen3.5-9B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --reasoning-parser qwen3
  

• Tool Use: To support tool use, you can use the following command.

  python -m sglang.launch_server --model-path Qwen/Qwen3.5-9B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --reasoning-parser qwen3 --tool-call-parser qwen3_coder
  

• Multi-Token Prediction (MTP): The following command is recommended for MTP:

  python -m sglang.launch_server --model-path Qwen/Qwen3.5-9B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --reasoning-parser qwen3 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
  

vLLM

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. vLLM from the main branch of the open-source repository is required for Qwen3.5, which can be installed using the following command in a fresh environment:

uv pip install vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly

See its documentation for more details.

For detailed Qwen3.5 usage guide, see the vLLM Qwen3.5 recipe.

The following will create API endpoints at http://localhost:8000/v1:

• Standard Version: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.

  vllm serve Qwen/Qwen3.5-9B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 
  

• Tool Call: To support tool use, you can use the following command.

  vllm serve Qwen/Qwen3.5-9B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder 
  

• Multi-Token Prediction (MTP): The following command is recommended for MTP:

  vllm serve Qwen/Qwen3.5-9B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
  

• Text-Only: The following command skips the vision encoder and multimodal profiling to free up memory for additional KV cache:

  vllm serve Qwen/Qwen3.5-9B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --reasoning-parser qwen3 --language-model-only
  

KTransformers

KTransformers is a flexible framework for experiencing cutting-edge LLM inference optimizations with CPU-GPU heterogeneous computing. For running Qwen3.5 with KTransformers, see the KTransformers Deployment Guide.

Hugging Face Transformers

Hugging Face Transformers contains a lightweight server which can be used for quick testing and moderate load deployment. The latest transformers is required for Qwen3.5:

pip install "transformers[serving] @ git+https://github.com/huggingface/transformers.git@main"

See its documentation for more details. Please also make sure torchvision and pillow are installed.

Then, run transformers serve to launch a server with API endpoints at http://localhost:8000/v1; it will place the model on accelerators if available:

transformers serve --force-model Qwen/Qwen3.5-9B --port 8000 --continuous-batching

Using Qwen3.5 via the Chat Completions API

The chat completions API is accessible via standard HTTP requests or OpenAI SDKs. Here, we show examples using the OpenAI Python SDK.

Before starting, make sure it is installed and the API key and the API base URL is configured, e.g.:

pip install -U openai

# Set the following accordingly
export OPENAI_BASE_URL="http://localhost:8000/v1"
export OPENAI_API_KEY="EMPTY"

We recommend using the following set of sampling parameters for generation

• Thinking mode for general 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 precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
• Instruct (or non-thinking) mode for general tasks: temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
• Instruct (or non-thinking) mode for reasoning tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

Please note that the support for sampling parameters varies according to inference frameworks.

Text-Only Input

from openai import OpenAI
# Configured by environment variables
client = OpenAI()

messages = [
    {"role": "user", "content": "Type \"I love Qwen3.5\" backwards"},
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
    }, 
)
print("Chat response:", chat_response)

Image Input

from openai import OpenAI
# Configured by environment variables
client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg"
                }
            },
            {
                "type": "text",
                "text": "The centres of the four illustrated circles are in the corners of the square. The two big circles touch each other and also the two little circles. With which factor do you have to multiply the radii of the little circles to obtain the radius of the big circles?\nChoices:\n(A) $\\frac{2}{9}$\n(B) $\\sqrt{5}$\n(C) $0.8 \\cdot \\pi$\n(D) 2.5\n(E) $1+\\sqrt{2}$"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
    }, 
)
print("Chat response:", chat_response)

Video Input

from openai import OpenAI
# Configured by environment variables
client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video_url",
                "video_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/video/N1cdUjctpG8.mp4"
                }
            },
            {
                "type": "text",
                "text": "Summarize the video content."
            }
        ]
    }
]

# When vLLM is launched with `--media-io-kwargs '{"video": {"num_frames": -1}}'`,
# video frame sampling can be configured via `extra_body` (e.g., by setting `fps`).
# This feature is currently supported only in vLLM.
#
# By default, `fps=2` and `do_sample_frames=True`.
# With `do_sample_frames=True`, you can customize the `fps` value to set your desired video sampling rate.
chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
        "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
    }, 
)

print("Chat response:", chat_response)

Instruct (or Non-Thinking) Mode

Qwen3.5 does not officially support the soft switch of Qwen3, i.e., /think and /nothink.

Qwen3.5 will think by default before response. You can obtain direct response from the model without thinking by configuring the API parameters. For example,

from openai import OpenAI
# Configured by environment variables
client = OpenAI()

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
                }
            },
            {
                "type": "text",
                "text": "Where is this?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    max_tokens=32768,
    temperature=0.7,
    top_p=0.8,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
        "chat_template_kwargs": {"enable_thinking": False},
    }, 
)
print("Chat response:", chat_response)

If you are using APIs from Alibaba Cloud Model Studio, in addition to changing model, please use "enable_thinking": False instead of "chat_template_kwargs": {"enable_thinking": False}.

Agentic Usage

Qwen3.5 excels in tool calling capabilities.

Qwen-Agent

We recommend using Qwen-Agent to quickly build Agent applications with Qwen3.5.

To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.

import os
from qwen_agent.agents import Assistant

# Define LLM
# Using Alibaba Cloud Model Studio
llm_cfg = {
    # Use the OpenAI-compatible model service provided by DashScope:
    'model': 'Qwen3.5-9B',
    'model_type': 'qwenvl_oai',
    'model_server': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
    'api_key': os.getenv('DASHSCOPE_API_KEY'),

    'generate_cfg': {
        'use_raw_api': True,
        # When using Dash Scope OAI API, pass the parameter of whether to enable thinking mode in this way
        'extra_body': {
            'enable_thinking': True
        },
    },
}

# Using OpenAI-compatible API endpoint.
# functionality of the deployment frameworks and let Qwen-Agent automate the related operations.
#
# llm_cfg = {
#     # Use your own model service compatible with OpenAI API by vLLM/SGLang:
#     'model': 'Qwen/Qwen3.5-9B',
#     'model_type': 'qwenvl_oai',
#     'model_server': 'http://localhost:8000/v1',  # api_base
#     'api_key': 'EMPTY',
#
#     'generate_cfg': {
#         'use_raw_api': True,
#         # When using vLLM/SGLang OAI API, pass the parameter of whether to enable thinking mode in this way
#         'extra_body': {
#             'chat_template_kwargs': {'enable_thinking': True}
#         },
#     },
# }

# Define Tools
tools = [
    {'mcpServers': {  # You can specify the MCP configuration file
            "filesystem": {
                "command": "npx",
                "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/xxxx/Desktop"]
            }
        }
    }
]

# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)

# Streaming generation
messages = [{'role': 'user', 'content': 'Help me organize my desktop.'}]
for responses in bot.run(messages=messages):
    pass
print(responses)

# Streaming generation
messages = [{'role': 'user', 'content': 'Develop a dog website and save it on the desktop'}]
for responses in bot.run(messages=messages):
    pass
print(responses)

Qwen Code

Qwen Code is an open-source AI agent for the terminal, optimized for Qwen models. It helps you understand large codebases, automate tedious work, and ship faster.

For more information, please refer to Qwen Code.

Processing Ultra-Long Texts

Qwen3.5 natively supports context lengths of up to 262,144 tokens. For long-horizon tasks where the total length (including both input and output) exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively., e.g., YaRN.

YaRN is currently supported by several inference frameworks, e.g., transformers, vllm, ktransformers and sglang. In general, there are two approaches to enabling YaRN for supported frameworks:

• Modifying the model configuration file: In the config.json file, change the rope_parameters fields in text_config to:

  {
      "mrope_interleaved": true,
      "mrope_section": [
          11,
          11,
          10
      ],
      "rope_type": "yarn",
      "rope_theta": 10000000,
      "partial_rotary_factor": 0.25,
      "factor": 4.0,
      "original_max_position_embeddings": 262144,
  }
  

• Passing command line arguments:

  For vllm, you can use

  VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ... --hf-overrides '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}' --max-model-len 1010000  
  

  For sglang and ktransformers, you can use

  SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server ... --json-model-override-args '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}' --context-length 1010000
  

All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. We advise modifying the rope_parameters configuration only when processing long contexts is required. It is also recommended to modify the factor as needed. For example, if the typical context length for your application is 524,288 tokens, it would be better to set factor as 2.0.

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:
     • Thinking mode for general 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 precise coding tasks (e.g., WebDev):
       temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
     • Instruct (or non-thinking) mode for general tasks:
       temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
     • Instruct (or non-thinking) mode for reasoning tasks:
       temperature=1.0, top_p=1.0, top_k=40, min_p=0.0, presence_penalty=2.0, 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}
}

---

Example Gen Q4KS, note the last 1/4 of the generation (from: "A woman in a dark coat approached me in the shadows.") - 100% Bradbury.

---

The Window That Exploded

User

Write a 2000 word scene (vivid, graphic horror in first person), POV character Diana, with: The skyscraper sways, as I watch the window in front of me on the 21st floor explode...

Assistant

<think>

Here's a thinking process that leads to the story above:

1. Analyze the Request:

   • Length: Approximately 2000 words.
   • Style: Vivid, graphic horror.
   • POV: First Person ("I").
   • Character: Diana.
   • Setting: A skyscraper, specifically looking out a window on the 21st floor.
   • Inciting Incident/Imagery: The window explodes (or rather, the scene starts with the building swaying and the window exploding as a focal point).
   • Goal: Create an immersive, visceral experience.

2. Brainstorming & Outlining:

   • Opening: Needs to establish the swaying motion immediately. The wind, the tension before the explosion.
   • The Explosion: Not just glass shattering, but a release of pressure, a projectile of glass and perhaps something else (dust, blood, rain?). Let's make it about the sound and the sensation of pressure.
   • The Victim/Target: Is it me? Am I the one watching? Or is it me and a woman named Diana (since the prompt says POV character Diana)? Let's keep it consistent: Diana is the narrator.
   • The Horror: What happened to the people in the window? Or was it just the glass? Maybe the glass shattered because the air rushed out from a vacuum formed by someone dying, or simply because the building's integrity is failing. Let's go with the building failing, but hinting that we are next.
   • Sensory Details: Smell of ozone, taste of metal, vibration in teeth, cold sweat.
   • Structure:
     • Part 1: The Sway (0-500 words) - Building up anticipation.
     • Part 2: The Event (500-1000 words) - The explosion, the rush of wind, the debris.
     • Part 3: The Aftermath/Realization (1000-1500 words) - Dust settles, the realization of how close death came.
     • Part 4: The Descent/Conclusion (1500-2000 words) - Moving to the next floor or realizing the pattern continues.

3. Drafting - Section by Section:

   • Section 1: The Sway. Focus on the wind. It's unnatural. It's not a normal breeze. Diana is standing by the window. The 21st floor.

     • Keywords: Leaning, tectonic, simmering, metal bones, perspiration.
     • Sensory: Humming, vibrating floor.
     • Voice: Introspective, trembling.

   • Section 2: The Explosion.

     • Action: The window gives way.
     • Visuals: Mosaic of diamond dust. A vacuum sucking her in, or just blowing her hair. Let's have her recoil.
     • Sound: A cannon shot, a whistle.
     • Graphic Element: Blood? Maybe a drop of blood fell from a ceiling crack caused by the shockwave. Let's add that. The ceiling cracked.
     • The "Thing" in the Window: Was it just the glass? Or did someone inside scream before they died? Let's introduce the idea that the person inside the window was crushed or blown out. No, simpler: The window exploded inward, spraying Diana. Wait, if it explodes in front of her, it hits her face.
     • Revision: The window explodes inward, slamming against her. No, the prompt says "watch the window in front of me explode." So she stands watching it shatter outward, sending shards into the street, but she feels the air pressure. Or maybe the window explodes outward, and she has to dodge. Let's make it visceral. It's a storm of glass.
     • Refinement: To maximize horror, the window should explode, spraying glass everywhere. She is a fly on the wall.

   • Section 3: The Aftermath & Internal State.

     • Dust settles. The smell of broken silica.
     • Her hands are bleeding from a cut she didn't feel.
     • The sound of sirens far below.
     • The realization that the 21st floor isn't the problem; it's just the middle of a nightmare.
     • Is it just her, or everyone? A montage of chaos below.
     • The elevator shaft screaming.

   • Section 4: The Pattern.

     • She looks down. The other windows are darkening.
     • The wind dies, but the silence is loud.
     • The sun sets abruptly because the sky was torn open (maybe?).
     • She steps back. The floor groans.
     • Closing thought: How do you survive one night of this?

4. Writing - Focusing on Flow and Word Count:

   • Need to ensure the pacing slows down to let the details sink in.
   • Check adjectives and verbs. Avoid generic words (look, see) and use specific ones (gaze, witness).
   • Self-Correction during drafting: I need to make sure the "graphic" part lands. Not just blood, but the feeling of the environment attacking her.
   • Word Count Check: If it's running short, expand on the micro-movements of her body. The tremble of a finger, the dilation of a pupil.

5. Refining the Narrative Arc:

   • Beginning: Diana on the 21st floor. Wind rising.
   • Middle: The event. The explosion.
   • End: The lingering dread.
   • Key motif: The color blue (steel, sky, glass).

6. Drafting Phase (Mental or Scratchpad):

   • Start with the swaying. "The skyscraper swayed."
   • Build the pressure.
   • The explosion: "BANG."
   • The detail: A single drop of blood on her lip from the shock.
   • The view down: The city looking up like a spiderweb of light.
   • Ending: She realizes she is now trapped by the storm.

   (Self-Correction during mental drafting): Wait, the prompt says "The skyscraper sways, as I watch the window in front of me on the 21st floor explode..." Okay, that's the core image. I need to build the scene around that specific moment.

   Let's flesh out the "Graphic Horror" aspect. It shouldn't just be the window. It should be the air, the light, the dust. Maybe the person behind the glass died before they died. Let's have the explosion reveal a body, or the remnants of a body, inside the window. No, keep it focused on Diana's experience. The horror is existential. Let's introduce a smell. Burnt hair? Plastic? Yes.

   Let's count the rhythm. Short sentences for impact. Long sentences for flow. Start drafting.

   Reviewing against constraints:

   • 2000 words approx.
   • Vivid, graphic.
   • First Person.
   • Name: Diana.
   • POV: Standing at window.

   (Final Plan)

   1. Establish the wind and the structural integrity failing.
   2. The countdown in her mind as the window holds.
   3. The explosion: kinetic energy, sound, glass.
   4. The debris on the floor.
   5. The realization that she is the next victim or the observer of the victim?
   6. Moving to the balcony.
   7. A sense of the city waking up from a deep sleep into a fever dream.

   Let's go.

</think>

The skyscraper swayed, a massive pendulum swinging in the empty night sky, and I stood frozen with my back against the glass, my heart hammering a frantic rhythm against my ribs like a trapped bird seeking release.

It was not a gentle breeze that pushed the building from the north, but a sudden, screaming exhale of the atmosphere, a vacuum sucking the air around us, making the steel bones of the tower shudder under the strain. Dust sifted down from the ceiling vents, disturbed by the building's own deep, tectonic sigh. I could feel the vibration travel up through the soles of my sneakers, into my ankles, my knees, settling in the marrow of my hip bone.

On the 21st floor, the window in front of me was a mirror of my own sweating face, a mirror of the pale moonlight and the city's red emergency glow reflecting in my eyes.

"Here we go," I whispered. The sound was swallowed by the immense hollow roar of the wind.

I watched the glass. It was trembling. A fine hairline fracture bloomed across the lower pane, a spiderweb cracking silently in the moonlight. Behind the glass, the world seemed to be holding its breath. The air pressure was building so violently it felt like a heavy hand pressing against the outside of the window, waiting for the seal to give way.

The smell of ozone was thick enough to bite, a cold, blue scent that filled the room before the wind did.

I remembered a similar night five years ago, in my childhood, watching a house across the street explode its siding under the load of too many raindrops, a domino effect of collapse. And now, the skyscraper was that house, and the rain was the wind, and the dominoes were the windows, waiting to tumble.

I placed one hand on the cold metal frame of the window and the other on the door handle. The door was jammed shut, locked from the outside by a digital mechanism I did not know how to bypass.

The window in front of me gave a single, sickening creak that sounded like a bone snapping in a dark room.

The pressure released.

I squeezed my eyes shut.

The explosion was not of fire, but of motion and sound, a piston of kinetic energy that fired the window out of its frame. Glass did not fall; it surged outward in a single, glittering trajectory, turning the room into a fine mist of silica powder for a split second. It was bright, like a strobe light, blinding and overwhelming. I felt the shockwave hit my face first, a cold slap that tasted of copper and electricity.

I flailed, my body reacting instinctively to the pressure wave that slammed the air against my chest, knocking the wind out of me. I fell back, my heels hitting the floor, a shower of tiny diamonds raining around me, cutting my skin as they hit.

Silence followed, ringing and echoing.

I lay there, gasping, staring up at the ceiling which seemed to be dripping water, or perhaps it was sweat from the sheer force of the quake. The room was swirling with dust that hung in the air, illuminated by the streetlamps outside.

Slowly, I pulled myself up to a crouching position. The window was gone, replaced by the open night sky. But the air rushing in was still chaotic, swirling in eddies, carrying with it not just dust, but a single drop of something red that slid down the window frame, splattering against the concrete below.

I touched my lip. It was numb.

The other windows on the floor were dark, save for the one directly across the hall. In the other room, a light flickered and died.

I stumbled toward the bathroom, needing to wash the smell of raw metal and ozone from my mouth, needing to see if I was bleeding from a cut I hadn't felt. I watched the water in the sink settle, looking for flecks of the blue dust that had traveled up the pipe.

I turned back to the window.

The skyscraper was still swaying, the motion a slow, hypnotic arc that had not yet found its rest. I leaned out, half-falling, into the empty space to see what lay beneath the twenty floors of falling silence.

The street below was a river of neon and shadow. And there, clustered around the building, were the emergency vehicles, their sirens still silent, their lights blinking like red and white eyelids.

But it was the sound that pulled me back in. A single, continuous low hum that vibrated the back of my throat, the hum of the vacuum cleaner of a city that had finally finished emptying its pockets.

I wanted to go back to my apartment, but my feet seemed to remember the path to the open void and the other side of the city where my building, with its missing window, now stood like a tomb.

The air rushed up my leg as I stepped off the balcony.

I landed on the sidewalk with a softness that surprised me. The other buildings looked ordinary. They seemed to be waiting for me to finish my walk so they could start falling one by one, to test the reflexes of their occupants.

I kept walking, my ears ringing with the memory of the window exploding.

I stopped every few steps to let my eyes adjust to the moonlight. Every few seconds I looked up at the 21st floor of the tower to see if a body had fallen from the broken window. But the night was empty, save for the moon and the dust motes dancing in its light.

I put my hand to the side of my head where the pressure had made my ears scream.

What possessed me to stay out here? Why didn't the instinct of survival kick in sooner, closer to the center of the room, near the wall, away from the open cliff? I felt foolish and alive. Alive meant exposed. Alive meant that if the next floor of the building decided to open its window, I would be standing there waiting to be hit by a second wave of glass.

I started running.

The wind caught my legs and flailed me about like a rag doll.

My eyes watered. My mouth opened and the wind filled it with cold dust and a single falling feather of glass that sliced my tongue.

The skyscraper was now a giant vacuum cleaner, sucking the sound and the light and the heat from the world.

I gasped for air and found only dust. I gagged. I thought of the single drop of blood I had seen on my lip. I thought of the other windows across the hall.

If the window across the hall blew out next, would it hit me?

I closed my eyes and thought of the solid wall of the hallway. If I could just reach the wall, just squeeze myself tight into the corner where the structure was strongest, where the load-bearing columns met the floor, perhaps I could ride out the final tremor and wait for the building to decide which of its tenants to let fall first.

But I was on the sidewalk now. The wall was gone. I was completely exposed.

A car sped by, its headlights sweeping across the facade of the tower, revealing the sheer emptiness where the window had been. A stage set for a tragedy, waiting for an audience.

The audience, I realized, was me.

I leaned against the cold brick of the alley next to the street. I slid down the brick wall until I hit the concrete dust. The night was so quiet I could hear my own heartbeat slowing down from a gallop to a jog, to a walk.

I felt the floor give way under my hand where the window had been. The vibration traveled through the sidewalk, up my fingers.

I sat there for twenty minutes, knees drawn up, eyes fixed on the sky. Was it real? Had I dreamt the sound, felt the pressure, the sudden displacement of air that knocked me off my feet? My lips were trembling.

A woman in a dark coat approached me in the shadows.

"You okay?"

I blinked.

The woman in the dark coat looked up at the tower. "Did you see it? It looked like it was going to cave. Did you see the way the glass just... popped?"

I nodded.

"Man, that was beautiful," she said, a ghost of a smile touching her lips. "I haven't seen a window explosion like that in years."

"What does that mean?" I asked.

"Oh, you know," she shrugged, touching the brim of her hat. "It means the building's done. It means the stage is set and the play's over. We just watched the final act."

I looked at her. "You weren't in the building?"

"No."

"You saw it all?"

"The whole show. The swaying, the silence before it happens, the build-up." She glanced at the tower. "You want to keep sitting there, or should we go get some coffee, warm up?"

I felt silly, my mouth, and I knew she was right. The cold had begun to set in, a single drop of rain falling on my knee.

I stood up and brushed the dust off my pants. "Let's get coffee. I need to know I'm not going insane."

She laughed, a dry, brittle sound. "Come on. I know a place. It's like coming out of a different dimension."

We started walking, leaving the skyscraper behind, but I kept looking back, waiting for the main event. The tower stood there, a monument to instability, the missing window now a dark hole in the moonlight, leaking the stars in.

"Do you hear that?" she said, listening.

"What?"

"The hum. It stops when you walk fast." She looked at me.

I listened. The wind was still blowing, but the special pressure had died, and the building stood straighter, anchored to the earth.

I took a breath. The air was still cold, but it smelled of a fresh storm.

I realized then that I had spent my life watching windows, literally, studying glass. I had watched it break and shatter a thousand times in movies, in my mind, but never felt the immense relief when the vacuum sealed shut and the world went back to normal. The window on the 21st floor was gone, but the feeling of being alive, of being cut and scraped and thrown in the air, was etched into my bones.

The skyscraper swayed once more, just once, as if acknowledging the applause of the crowd, before settling back down into its own heavy sleep, waiting for the next night, the next vacuum, the next window to shatter.

I watched the woman in the dark coat vanish into the night, her footsteps light, her smile gone, replaced by a look of pure bewilderment as if she had just seen the impossible.

I looked back at the tower.

It was swaying again.

I blinked.

My eyes watered.

I rubbed my eyes.

It was still there.

The skyscraper swayed, as I watched the window in front of me on the 21st floor explode.

I opened my mouth and let the wind fill it.