Qwen

/

Qwen3.8-27B-FP8

Image-Text-to-Text

Transformers

Safetensors

qwen3_5

conversational

fp8

Model card Files Files and versions

xet

Community

Qwen3.8-27B-FP8

Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.

Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.

Qwen3.8 Highlights

Qwen3.8-27B features the following enhancements:

• Core Capabilities: Comprehensive improvements across coding, professional work, research, and long-horizon agentic tasks.

• Agent Execution: Stronger autonomous planning and better handling of environment feedback, leading to more reliable end-to-end task completion.

• Downstream Compatibility: Broader support for popular harnesses and development tools, making it easier to integrate into your existing stack.

• Flexible Thinking Control: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with reasoning_effort, and reasoning context from historical messages is retained via preserve_thinking.

• Vision-Language Understanding: Native support for image and video understanding, from STEM diagrams and documents to hour-scale videos.

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: 248,320 (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: 17,408

  • LM Output: 248,320 (Padded)

  • MTP (Multi-Token Prediction): trained with multiple steps

• Context Length: 262,144 natively and extensible up to 1,000,000 tokens.

Benchmark Results

Text Performance

Agentic terminal coding

Terminal Bench 2.1 (Terminus)

Agentic coding

SWE-bench Pro

Repo-level code generation

NL2Repo-Bench

Agentic coding

DeepSWE 1.1

Software engineering

QwenSWEBench

Long-horizon office work

CoWorkBench

Professional job tasks

JobBench

Frontier agentic tasks

Agents' Last Exam

Pass@1

20.4

Score

42.9

Pass@1

10.6

Score

27.3

Pass@1

13.2

Score

33.6

Instruction following

IFBench

Scientific reasoning

GPQA Diamond

Multidisciplinary reasoning

HLE

Competitive coding

LiveCodeBench v6

	Qwen3.8-27B	Qwen3.6-27B	Qwen3.7-Plus	Muse Glimmer-30B	Opus4.6 Max
Coding
	73.0	63.4	64.0	51.7	78.2
	61.7	53.5	57.6	51.2	53.4
	42.3	36.2	41.1	--	47.6
	42.2	13.3	14.2	--	--
	79.0	49.3	59.2	--	63.8
Agent
	70.7	61.0	65.1	--	68.2
	33.4	21.8	27.6	--	--
				--	--
General
	79.5	69.1	79.1	77.0	62.5
	89.2	87.8	90.3	83.5	91.3
	30.8	24.0	34.7	22.0	40.0
	90.3	83.9	89.6	--	88.8

1. SWE-bench Pro: Except for Opus4.6 Max, which uses the officially reported score, all models are evaluated with the Claude Code harness at temp=1.0, top_p=0.95, and a 256K context window. Problematic tasks were corrected, and all baseline models were re-evaluated on the refined benchmark.

2. NL2Repo-Bench: Evaluated with the Claude Code harness. To prevent reward hacking, we disable Bash commands that attempt to access the specific repository, such as pip download, pip install, and git clone.

3. DeepSWE 1.1: Evaluated with the Claude Code harness at temp=1.0, top_p=0.95, and a 256K context window.

4. QwenSWEBench: In-house coding benchmark for evaluating models' software engineering capabilities. Evaluated with the Claude Code harness. Reporting avg@3 with an 8-hour timeout, max_tokens=32,768, temperature=1.0, and a 256K context window.

5. CoWorkBench: In-house cowork benchmark for evaluating long-horizon tasks across computer science, finance, law, medical, and other productivity domains.

6. HLE: Judged by GPT-4o.

7. The best result in each row is shown in bold.

8. Empty cells (--) indicate that results are not yet available or not applicable.

VL Performance

Computer use

OSWorld-Verified

Browser use

WebArena-Verified

Mobile use

AndroidWorld

Application recreation

RecreationBench

Multimodal tool use

ClawEval-MM

Pass@3

57.4

Average

56.9

Pass@3

42.6

Average

50.4

Pass@3

57.4

Average

60.1

Pass@3

52.5

Average

54.7

Multimodal software engineering

SWE-MM

Visual web development

Vision2Web

Visual math problem solving

MathVision

Without CI

90.0

With CI

94.6

Without CI

85.1

Without CI

90.3

Without CI

65.5

General visual reasoning

BabyVision

Without CI

65.7

With CI

85.6

Without CI

28.9

Without CI

64.7

With CI

70.4

Without CI

12.6

Scientific chart analysis

CharXiv (RQ)

Without CI

83.7

With CI

90.2

Without CI

78.4

Without CI

85.8

With CI

85.9

Without CI

66.0

Document intelligence

OmniDocBench 1.5

Real-world perception

RealWorldQA

Embodied intelligence

ERQA

	Qwen3.8-27B	Qwen3.6-27B	Qwen3.7-Plus	Muse Glimmer-30B	Opus4.6 Max
Agentic Multimodal Intelligence
	84.3	63.9	73.3	65.9	72.7
	64.8	48.8	55.3	--	--
	81.9	70.3	81.0	--	62.0
	47.1	29.8	30.2	--	--
				--
	38.6	25.7	30.0	--	27.1
	62.9	45.0	42.1	--	--
General Multimodal Intelligence
				--
				--
				78.8
	91.1	89.4	91.4	75.8	86.6
	85.9	84.1	86.9	--	73.9
	65.5	62.5	69.8	--	40.8

1. MathVision, BabyVision, and CharXiv (RQ): Where both settings are available, cells report “Without CI” and “With CI” separately; otherwise, only the available setting is shown. A small number of incorrect ground-truth annotations in MathVision and CharXiv (RQ) were corrected following manual verification, and all reported scores on those benchmarks were computed using the corrected annotations.

2. MathVision: Qwen3.8-27B is evaluated using the fixed prompt: “Please reason step by step, and put your final answer within \boxed{}.” For the remaining models, we report the higher score from two prompt variants—one with and one without the \boxed{} formatting requirement.

3. WebArena-Verified: Scores are computed with the official WebArena-Verified grader under the OSWorld scaffold.

4. RecreationBench: An in-house, long-horizon application-recreation benchmark designed to evaluate hybrid-agent capabilities across five platforms: desktop (Ubuntu, macOS, and Windows), mobile (Android), and the web.

5. ClawEval-MM: Scores are reported as “Pass@3 / average score.” Pass@3 is the percentage of tasks passed in at least one of three trials; the average score is the mean benchmark score across the three trials.

6. Vision2Web: Scores are averaged across the frontend, webpage, and website categories. Evaluations use the Claude Code harness and are judged by gpt-5.4-2026-03-05.

7. SWE-MM: Scores are evaluated on the Claude Code harness using the public dev split of SWE-bench Multimodal, with the modifications described in Appendix 8.3 of the Claude Opus 4.7 system card.

8. Empty cells (--) indicate that results are not yet available or not applicable.

Quickstart

For streamlined integration, we recommend using Qwen3.8 via APIs.

Serving Qwen3.8

Qwen3.8 can be deployed with popular inference frameworks, e.g.:

• SGLang: Qwen3.8 Cookbook

• vLLM: Qwen3.8 Recipe

• TokenSpeed: Qwen3.8 Recipe

API Usage

• Thinking Mode: temperature=1.0, 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

Qwen3.8 comes with official support for reasoning_effort, which can be used to adjust reasoning depth and control cost:

• xhigh (default): for complex tasks demanding thorough analysis

• medium: balancing accuracy and speed

• low: efficient reasoning optimizing for speed and cost

In addition, preserve_thinking is enabled by default for all workloads for the best out-of-the-box experience. To disable preserved thinking, refer to the examples here.

Chat Completions API

The Chat Completions API can be used with most inference frameworks, as well as Qwen Cloud. Before starting, make sure the OpenAI Python SDK is installed and the API key and the API base URL are configured, e.g.:

pip install -U openai

# Set the following accordingly
export OPENAI_BASE_URL='your-base-url'
export OPENAI_API_KEY='your-api-key'

Text-Only Input

from openai import OpenAI

client = OpenAI()

messages = [{"role": "user", "content": "Write a Python function to merge two sorted linked lists."}]

completion = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B-FP8",
    messages=messages,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,
            "preserve_thinking": True,
        },
    },
    reasoning_effort="xhigh",
    stream=True,
    stream_options={"include_usage": True},
)

reasoning_content = ""
answer_content = ""
is_answering = False
print("\n" + "=" * 20 + "Reasoning" + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
        continue

    delta = chunk.choices[0].delta

    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
        reasoning_content += delta.reasoning_content
    elif hasattr(delta, "reasoning") and delta.reasoning is not None:
        if not is_answering:
            print(delta.reasoning, end="", flush=True)
        reasoning_content += delta.reasoning

    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Answer" + "=" * 20 + "\n")
            is_answering = True
        print(delta.content, end="", flush=True)
        answer_content += delta.content

messages.append({
    "role": "assistant",
    "content": answer_content,
    "reasoning_content": reasoning_content,
    "reasoning": reasoning_content,
})

Image Input

from openai import OpenAI

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/Qwen3.8-27B-FP8",
    messages=messages,
)
print("Chat response:", chat_response)

Video Input

from openai import OpenAI

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?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B",
    messages=messages,
)

print("Chat response:", chat_response)

Instruct (or Non-Thinking) Mode

Qwen3.8-27B will think by default before responding. You can obtain a direct response from the model without thinking by configuring the API parameters. For example,

from openai import OpenAI

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/Qwen3.8-27B-FP8",
    messages=messages,
    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)

Disable Preserved Thinking

By default, Qwen3.8 retains thinking blocks from all historical messages, maintaining a complete reasoning trace across the conversation. This behavior, known as preserved thinking, ensures full context continuity and is especially beneficial for agent scenarios where decision consistency and reduced redundant reasoning are critical. It also improves KV cache utilization, optimizing inference efficiency in both thinking and non-thinking modes.

If you prefer to retain only the thinking blocks from the latest user message, you can disable this behavior by setting preserve_thinking to False:

from openai import OpenAI

client = OpenAI()
messages = [...]
chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-27B-FP8",
    messages=messages,
    extra_body={
        "chat_template_kwargs": {"preserve_thinking": False},
    },
)
print("Chat response:", chat_response)

Best Practices

To achieve optimal performance, we recommend the following settings:

1. Sampling Parameters: We suggest using the following sets of sampling parameters:

• Thinking Mode: temperature=1.0, 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

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

2. Adequate Output Length: To optimize performance on agentic tasks, we recommend allocating sufficient output length to allow the model to generate detailed and comprehensive responses. For frameworks that support separate token limits for internal reasoning and final outputs, we suggest the following configuration within the 1M context length:

• Reasoning Content: Set the maximum output length to 262,144 tokens.

• Final Response: Set the maximum output length to 131,072 tokens.

1. These settings provide the necessary capacity for complex reasoning while ensuring ample space for high-quality final deliverables.

2. Processing Ultra-Long Texts: Qwen3.8-27B 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.

3. YaRN is currently supported by several inference frameworks, e.g., vLLM, SGLang, and TokenSpeed. 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 1000000

• For SGLang, 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 1000000

• For TokenSpeed, you can use

TOKENSPEED_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 tokenspeed 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 1000000

1. 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.

1. 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}

1. 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{qwen38,
    title = {{Qwen3.8-Max}: A New Bar for Coding and Cowork},
    url = {https://qwen.ai/blog?id=qwen3.8},
    author = {{Qwen Team}},
    month = {August},
    year = {2026}
}

Downloads last month

Safetensors

Model size

28B params

Tensor type

BF16

·

F8_E4M3

·

Model tree for Qwen/Qwen3.8-27B-FP8

Base model

Qwen/Qwen3.8-27B

Quantized

(125)

this model

Space using Qwen/Qwen3.8-27B-FP8 1

Collection including Qwen/Qwen3.8-27B-FP8

Qwen3.8

Collection

4 items • Updated 1 day ago • 165