What is Mungert/Qwen3.6-27B-GGUF?

--- library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE pipeline_tag: image-text-to-text --- # Qwen3.6-27B GGUF Models ## Model Generation Details This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`7c158fbb4`](https://github.com/ggerganov/llama.cpp/commit/7c158fbb4aec1bdc9c81d6ca0e785139f4826fae). --- Click here to get info on choosing the right GGUF model format --- # Qwen3.6-27B [![Qwen Chat](https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5)](https://c…

What license applies to Mungert/Qwen3.6-27B-GGUF?

License: apache-2.0. Verify terms on Hugging Face before commercial use.

How do I run Mungert/Qwen3.6-27B-GGUF locally?

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: image-text-to-text.

Model Intelligence Sheet

Mungert/Qwen3.6-27B-GGUF overview

Q: How much VRAM or disk space does Mungert/Qwen3.6-27B-GGUF need?

Runs locally from ~13.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

<span style="color: 7FFF7F;" Qwen3.6 27B GGUF Models</span <span style="color: 7F7FFF;" Model Generation Details</span This model was generated using llama.cpp…

transformersggufimage-text-to-textlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~13.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads

4,511

Likes

Pipeline

image-text-to-text

Author

Mungert

Repository Files & Downloads

18 GGUF files detected

Direct downloads for local inference

File	Type	Quantization	Size	Link
Qwen3.6-27B-bf16_q8_0.gguf	GGUF	BF16	38.46 GB	Download
Qwen3.6-27B-f16_q8_0.gguf	GGUF	F16	38.46 GB	Download
Qwen3.6-27B-imatrix.gguf	GGUF	GGUF	13.0 MB	Download
Qwen3.6-27B-iq3_m.gguf	GGUF	IQ3_M	12.63 GB	Download
Qwen3.6-27B-iq4_nl.gguf	GGUF	IQ4_NL	14.71 GB	Download
Qwen3.6-27B-iq4_xs.gguf	GGUF	IQ4_XS	14.68 GB	Download
Qwen3.6-27B-q2_k_m.gguf	GGUF	Q2_K_M	10.63 GB	Download
Qwen3.6-27B-q3_k_m.gguf	GGUF	Q3_K_M	13.62 GB	Download
Qwen3.6-27B-q3_k_s.gguf	GGUF	Q3_K_S	13.25 GB	Download
Qwen3.6-27B-q4_0.gguf	GGUF	Q4_0	15.52 GB	Download
Qwen3.6-27B-q4_1.gguf	GGUF	Q4_1	16.07 GB	Download
Qwen3.6-27B-q4_k_m.gguf	GGUF	Q4_K_M	16.83 GB	Download
Qwen3.6-27B-q4_k_s.gguf	GGUF	Q4_K_S	15.67 GB	Download
Qwen3.6-27B-q5_0.gguf	GGUF	Q5_0	18.40 GB	Download
Qwen3.6-27B-q5_1.gguf	GGUF	Q5_1	19.84 GB	Download
Qwen3.6-27B-q5_k_m.gguf	GGUF	Q5_K_M	19.41 GB	Download
Qwen3.6-27B-q6_k_m.gguf	GGUF	Q6_K_M	21.53 GB	Download
Qwen3.6-27B-q8_0.gguf	GGUF	Q8_0	27.05 GB	Download

Model Details

Model ID	Mungert/Qwen3.6-27B-GGUF
Author	Mungert
Pipeline	image-text-to-text
License	apache-2.0
Base model	—
Last modified	2026-06-08T21:14:13.000Z

Model README

---

library_name: transformers

license: apache-2.0

license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE

pipeline_tag: image-text-to-text

---

<span style="color: #7FFF7F;">Qwen3.6-27B GGUF Models</span>

<span style="color: #7F7FFF;">Model Generation Details</span>

This model was generated using llama.cpp at commit 7c158fbb4.

---

Click here to get info on choosing the right GGUF model format

</a>

---

Qwen3.6-27B

![Qwen Chat](https://chat.qwen.ai)

> [!Note]

> 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.

Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.

Qwen3.6 Highlights

This release delivers substantial upgrades, particularly in

Agentic Coding: the model now handles frontend workflows and repository-level reasoning with greater fluency and precision.
Thinking Preservation: we've introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead.

!Benchmark Results

For more details, please refer to our blog post Qwen3.6-27B.

Model Overview

Type: Causal Language Model with Vision Encoder
Training Stage: Pre-training & Post-training
Language Model

- Number of Parameters: 27B

- Hidden Dimension: 5120

- Token Embedding: 248320 (Padded)

- Number of Layers: 64

- Hidden Layout: 16 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))

- Gated DeltaNet:

- Number of Linear Attention Heads: 48 for V and 16 for QK

- Head Dimension: 128

- Gated Attention:

- Number of Attention Heads: 24 for Q and 4 for KV

- Head Dimension: 256

- Rotary Position Embedding Dimension: 64

- Feed Forward Network:

- Intermediate Dimension: 17408

- 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

<th style="padding:10px 7px;text-align:left;font-weight:600;border-bottom:2px solid #7c3aed;color:#7c3aed"></th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-27B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.5-397B-A17B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Gemma4-31B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Claude 4.5 Opus</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.6-35B-A3B</th><th style="padding:10px 7px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size: 14px;">Qwen3.6-27B</th></tr></thead>

<tbody>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Coding Agent</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Verified</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Pro</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SWE-bench Multilingual</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Terminal-Bench 2.0</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SkillsBench <sub><small>Avg5</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">QwenWebBench</td>

</tr>

<tr>

</tr>

<tr>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">QwenClawBench</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Knowledge</td></tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMLU-Redux</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SuperGPQA</td>

</tr>

<tr>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">STEM & Reasoning</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">GPQA Diamond</td>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">LiveCodeBench v6</td>

</tr>

<tr>

</tr>

<tr>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">IMOAnswerBench</td>

</tr>

<tr>

</tr>

</tbody>

</table>

SWE-Bench Series: Internal agent scaffold (bash + file-edit tools); temp=1.0, top_p=0.95, 200K context window. We correct some problematic tasks in the public set of SWE-bench Pro and evaluate all baselines on the refined benchmark.<br/>
Terminal-Bench 2.0: Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.<br/>
SkillsBench: Evaluated via OpenCode on 78 tasks (self-contained subset, excluding API-dependent tasks); avg of 5 runs.<br/>
NL2Repo: Others are evaluated via Claude Code (temp=1.0, top_p=0.95, max_turns=900).<br/>
QwenClawBench: A real-user-distribution Claw agent benchmark; temp=0.6, 256K ctx.<br/>
QwenWebBench: An internal front-end code generation benchmark; bilingual (EN/CN), 7 categories (Web Design, Web Apps, Games, SVG, Data Visualization, Animation, and 3D); auto-render + multimodal judge (code/visual correctness); BT/Elo rating system.<br/>
AIME 26: We use the full AIME 2026 (I & II), where the scores may differ from Qwen 3.5 notes.

</p>

</div>

Vision Language

<tbody>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">STEM & Puzzle</td></tr>

<tr>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MathVista <sub><small>mini</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">DynaMath</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VlmsAreBlind</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">General VQA</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RealWorldQA</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMStar</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MMBench<sub><small>EN-DEV-v1.1</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">SimpleVQA</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Document Understanding</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">CharXiv <sub><small>RQ</small></sub></td>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">OCRBench</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Spatial Intelligence</td></tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">CountBench</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RefCOCO <sub><small>avg</small></sub></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">EmbSpatialBench</td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">RefSpatialBench</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Video Understanding</td></tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VideoMME<sub><small>(w sub.)</sub></small></td>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">VideoMMMU</td>

</tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">MVBench</td>

</tr>

<tr><td colspan="7" style="padding:8px 12px;font-weight:600;color:#7c3aed;border-bottom:1px solid rgba(124, 58, 237, 0.2);background:rgba(124, 58, 237, 0.1)">Visual Agent</td></tr>

<tr>

</tr>

<tr>

<td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">AndroidWorld</td>

</tr>

</tbody>

</table>

Empty cells (--) indicate scores not yet available or not applicable.

</p>

</div>

Quickstart

For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API.

Serving Qwen3.6

Qwen3.6 can be served via APIs with popular inference frameworks.

In the following, we show example commands to launch OpenAI-Compatible API servers for Qwen3.6 models.

> [!Important]

> 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.

> [!Important]

> 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 Qwen3.6 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>=0.5.10 is recommended for Qwen3.6, which can be installed using the following command in a fresh environment:

uv pip install 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.

```shell

python -m sglang.launch_server --model-path Qwen/Qwen3.6-27B --port 8000 --tp-size 8 --mem-fraction-static 0.8 --context-length 262144 --reasoning-parser qwen3

```

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

```shell

python -m sglang.launch_server --model-path Qwen/Qwen3.6-27B --port 8000 --tp-size 8 --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:

```shell

python -m sglang.launch_server --model-path Qwen/Qwen3.6-27B --port 8000 --tp-size 8 --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

```

For detailed deployment guide, see the SGLang Qwen3.5 Cookbook.

vLLM

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.

vllm>=0.19.0 is recommended for Qwen3.6, which can be installed using the following command in a fresh environment:

uv pip install vllm --torch-backend=auto

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.

```shell

vllm serve Qwen/Qwen3.6-27B --port 8000 --tensor-parallel-size 8 --max-model-len 262144 --reasoning-parser qwen3

```

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

```shell

vllm serve Qwen/Qwen3.6-27B --port 8000 --tensor-parallel-size 8 --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:

```shell

vllm serve Qwen/Qwen3.6-27B --port 8000 --tensor-parallel-size 8 --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:

```shell

vllm serve Qwen/Qwen3.6-27B --port 8000 --tensor-parallel-size 8 --max-model-len 262144 --reasoning-parser qwen3 --language-model-only

```

For detailed deployment guide, see the vLLM Qwen3.5 Recipe.

KTransformers

KTransformers is a flexible framework for experiencing cutting-edge LLM inference optimizations with CPU-GPU heterogeneous computing.

For running Qwen3.6 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 Qwen3.6:

pip install "transformers[serving]"

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 Qwen/Qwen3.6-27B --port 8000 --continuous-batching

Using Qwen3.6 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"

> [!Tip]

> 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=0.0, 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: temperature=0.7, top_p=0.80, 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.

> [!Important]

> Qwen3.6 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.

Text-Only Input

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

messages = [
    {"role": "user", "content": "Type \"I love Qwen3.6\" backwards"},
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.6-27B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=0.0,
    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/Qwen3.6-27B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=0.0,
    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": "How many porcelain jars were discovered in the niches located in the primary chamber of the tomb?"
            }
        ]
    }
]

# 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/Qwen3.6-27B",
    messages=messages,
    max_tokens=81920,
    temperature=1.0,
    top_p=0.95,
    presence_penalty=0.0,
    extra_body={
        "top_k": 20,
        "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
    }, 
)

print("Chat response:", chat_response)

Instruct (or Non-Thinking) Mode

> [!Important]

> Qwen3.6 does not officially support the soft switch of Qwen3, i.e., /think and /nothink.

Qwen3.6 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/Qwen3.6/demo/RealWorld/RealWorld-04.png"
                }
            },
            {
                "type": "text",
                "text": "Where is this?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.6-27B",
    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)

> [!Note]

> 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}.

Preserve Thinking

By default, only the thinking blocks generated in handling the latest user message is retained, resulting in a pattern commonly as interleaved thinking.

Qwen3.6 has been additionally trained to preserve and leverage thinking traces from historical messages.

You can enable this behavior by setting the preserve_thinking option:

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

messages = [...]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.6-27B",
    messages=messages,
    max_tokens=32768,
    temperature=0.6,
    top_p=0.95,
    presence_penalty=0.0,
    extra_body={
        "top_k": 20,
        "chat_template_kwargs": {"preserve_thinking": True},
    }, 
)
print("Chat response:", chat_response)

> [!Note]

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

This capability is particularly beneficial for agent scenarios, where maintaining full reasoning context can enhance decision consistency and, in many cases, reduce overall token consumption by minimizing redundant reasoning. Additionally, it can improve KV cache utilization, optimizing inference efficiency in both thinking and non-thinking modes.

Agentic Usage

Qwen3.6 excels in tool calling capabilities.

Qwen-Agent

We recommend using Qwen-Agent to quickly build Agent applications with Qwen3.6.

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': 'qwen3.6-27b',
    '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,
            'preserve_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/Qwen3.6-27B',
#     '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, 'preserve_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

Qwen3.6 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:

```json

{

"mrope_interleaved": true,

"mrope_section": [

11,

"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

```shell

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

```shell

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

```

> [!NOTE]

> 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:

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=0.0, 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:

temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, 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.

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.

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"."

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,

```json

{"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{qwen3.6-27b,
    title  = {{Qwen3.6-27B}: Flagship-Level Coding in a {27B} Dense Model},
    author = {{Qwen Team}},
    month  = {April},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.6-27b}
}

---

<span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:

Choose an AI assistant type:

- TurboLLM (GPT-4.1-mini)

- HugLLM (Hugginface Open-source models)

- TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

Function calling against live network services
How small can a model go while still handling:

- Automated Nmap security scans

- Quantum-readiness checks

- Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

✅ Zero-configuration setup
⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

**It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
Create custom cmd processors to run .net code on Quantum Network Monitor Agents
Real-time network diagnostics and monitoring
Security Audits
Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a comprehensive security audit on my server"
'"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊

Run Mungert/Qwen3.6-27B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models