Qwen3.8-27B-GLQ-trellis-3inst-4bpw API & Inference Endpoint

Install

bash
pip install glq

Requires glq >= 0.7.0 — this checkpoint stores the trellis in the kernel (MMA-fragment) layout that the lookup-free 3INST CUDA kernels consume.

Use with vLLM (recommended)

python
from vllm import LLM, SamplingParams


def main():
    llm = LLM(
        model="xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw",
        quantization="glq",
        dtype="bfloat16",
        max_model_len=4096,
        limit_mm_per_prompt={"image": 0, "video": 0, "audio": 0},  # text-only serving
    )
    out = llm.generate(["The capital city of New Zealand is"],
                       SamplingParams(max_tokens=64, temperature=0))
    print(out[0].outputs[0].text)


# The __main__ guard is REQUIRED when running this as a script. vLLM switches to the
# "spawn" multiprocessing start method once CUDA is initialised, so its worker processes
# re-import this file; without the guard the script spawns itself recursively and dies
# with "An attempt has been made to start a new process before the current process has
# finished its bootstrapping phase" — before the model ever loads.
if __name__ == "__main__":
    main()

glq registers with vLLM automatically via its plugin entry point — no extra import needed.

Serve with tensor parallelism 1 (the default): GLQ trellis layers do not support TP sharding.

Use with Transformers

Not supported for this architecture yet: the hybrid GatedDeltaNet decoder under a multimodal wrapper is only validated on vLLM. Use the vLLM snippet above.

Use with coding agents (pi-code, opencode)

Serve an OpenAI-compatible endpoint, then point your agent at it:

bash
vllm serve xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw --port 8000

pi-code — ~/.pi/agent/models.json:

json
{
  "providers": {
    "glq": {
      "baseUrl": "http://localhost:8000/v1",
      "api": "openai-completions",
      "apiKey": "glq",
      "models": [
        {
          "id": "xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw"
        }
      ]
    }
  }
}

opencode — ~/.config/opencode/opencode.json:

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "glq": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GLQ (local vLLM)",
      "options": {
        "baseURL": "http://localhost:8000/v1",
        "apiKey": "glq"
      },
      "models": {
        "xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw": {
          "name": "Qwen3.8-27B-GLQ-trellis-3inst-4bpw"
        }
      }
    }
  }
}

Benchmarks

Table with columns: Benchmark, Metric, GLQ 4bpw
Benchmark	Metric	GLQ 4bpw
AIME-2026 (avg@8, thinking, 32k budget, temp 1.0/top_k 20, RTX PRO 6000; all three arms same harness+settings — a tie within n=30 noise, not a ranking)	accuracy (n=30)	90.4% (bf16: 87.9%, NVFP4 unsloth: 87.9%)
AIME-2026 eval wall-clock (same 240-sample batched workload, RTX PRO 6000 — an aggregate-throughput proxy, not single-stream decode)	duration	2h47m (bf16: 2h37m, NVFP4: 1h02m)
Wikitext-2 perplexity (vLLM prompt-logprobs, 128 chunks x 2048 tok, RTX PRO 6000)	perplexity	7.06 (bf16: 7.02, NVFP4: 7.17)
Weights (vLLM text-only serving; NVFP4 is safetensors size)	GiB	16.68 (bf16: 50.22, NVFP4: 20.47 loaded)
Decode, batch 1 (L4 24 GB, 4096 ctx, CUDA graphs)	tok/s

Single-run measurements; small-n results are noisy estimates. Setup details per row.

How GLQ works

A randomized Hadamard transform (a fixed random sign-flip + Hadamard rotation on each side) makes the weights and the calibration Hessian incoherent — spreading outliers so they quantize well. LDLQ then rounds the weights with error feedback across the remaining input dimensions via the Hessian's LDL factorization. Instead of a per-group lattice codebook, GLQ here uses trellis-coded quantization (TCQ, from QTIP): each 16×16 weight tile is encoded as a tail-biting Viterbi sequence over a dimension-256 trellis code, reaching a higher effective quantization dimension than an 8-D lattice at the same bit-rate. Decoding is a small look-up plus a few arithmetic ops per weight; a fused CUDA kernel keeps the weights compressed in VRAM and decodes them inline.

The "Golay/Leech" in the project name refers to the lattice codebooks GLQ also ships (E8 and its higher-dimensional cousins). Code, kernels and quantizer: GLQ on GitHub.

Qwen3.8-27B

[!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, TokenSpeed, etc.

[!Tip] For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates.

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

Benchmark Results

Text Performance

VL Performance

Quickstart

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

Serving Qwen3.8

[!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, vLLM, or TokenSpeed are recommended.

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

API Usage

[!Important] Qwen3.8 models operate in thinking mode by default, generating thinking content signified by <think>\n...</think>\n\n before producing the final response. To disable thinking content and obtain a direct response, refer to the examples here.

[!Tip] We recommend using the following sets of sampling parameters for generation:

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

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

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.

[!Tip] In multi-turn agentic tasks, lower reasoning effort does not always reduce overall task completion time. Although it may produce faster per-turn responses, it can also lead to insufficient analysis, more failures, and repeated retries, which may increase total latency and token consumption.

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.:

shell
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

python
from openai import OpenAI
# Configured by environment variables
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",
    messages=messages,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,  # on by default
            "preserve_thinking": True, # on by default
        },
    },
    reasoning_effort="xhigh",  # xhigh by default; supported levels are xhigh, medium, and low
    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

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

Video Input

python
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?"
            }
        ]
    }
]

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

# 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/Qwen3.8-27B",
#     messages=messages,
#     extra_body={
#         "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
#     }, 
# )

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,

python
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/Qwen3.8-27B",
    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)

[!Note] If you are using APIs from Qwen Cloud, in addition to changing model, please use "enable_thinking": False instead of "chat_template_kwargs": {"enable_thinking": False}.

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:

python
from openai import OpenAI

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

[!Note] If you are using APIs from Qwen Cloud, in addition to changing model, please use "preserve_thinking": False directly instead of wrapping it in chat_template_kwargs.

Best Practices

To achieve optimal performance, we recommend the following settings:

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
For supported frameworks, you can adjust the 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.

Citation

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

bibtex
@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}
}

Derivative work of Qwen/Qwen3.8-27B, quantized with GLQ. It inherits the base model's license (apache-2.0) — please respect the base model's terms.

⭐ GLQ on GitHub

Install

bash
pip install glq

Requires glq >= 0.7.0 — this checkpoint stores the trellis in the kernel (MMA-fragment) layout that the lookup-free 3INST CUDA kernels consume.

Use with vLLM (recommended)

python
from vllm import LLM, SamplingParams


def main():
    llm = LLM(
        model="xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw",
        quantization="glq",
        dtype="bfloat16",
        max_model_len=4096,
        limit_mm_per_prompt={"image": 0, "video": 0, "audio": 0},  # text-only serving
    )
    out = llm.generate(["The capital city of New Zealand is"],
                       SamplingParams(max_tokens=64, temperature=0))
    print(out[0].outputs[0].text)


# The __main__ guard is REQUIRED when running this as a script. vLLM switches to the
# "spawn" multiprocessing start method once CUDA is initialised, so its worker processes
# re-import this file; without the guard the script spawns itself recursively and dies
# with "An attempt has been made to start a new process before the current process has
# finished its bootstrapping phase" — before the model ever loads.
if __name__ == "__main__":
    main()

glq registers with vLLM automatically via its plugin entry point — no extra import needed.

Serve with tensor parallelism 1 (the default): GLQ trellis layers do not support TP sharding.

Use with Transformers

Not supported for this architecture yet: the hybrid GatedDeltaNet decoder under a multimodal wrapper is only validated on vLLM. Use the vLLM snippet above.

Use with coding agents (pi-code, opencode)

Serve an OpenAI-compatible endpoint, then point your agent at it:

bash
vllm serve xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw --port 8000

pi-code — ~/.pi/agent/models.json:

json
{
  "providers": {
    "glq": {
      "baseUrl": "http://localhost:8000/v1",
      "api": "openai-completions",
      "apiKey": "glq",
      "models": [
        {
          "id": "xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw"
        }
      ]
    }
  }
}

opencode — ~/.config/opencode/opencode.json:

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "glq": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GLQ (local vLLM)",
      "options": {
        "baseURL": "http://localhost:8000/v1",
        "apiKey": "glq"
      },
      "models": {
        "xv0y5ncu/Qwen3.8-27B-GLQ-trellis-3inst-4bpw": {
          "name": "Qwen3.8-27B-GLQ-trellis-3inst-4bpw"
        }
      }
    }
  }
}

Benchmarks

Table with columns: Benchmark, Metric, GLQ 4bpw
Benchmark	Metric	GLQ 4bpw
AIME-2026 (avg@8, thinking, 32k budget, temp 1.0/top_k 20, RTX PRO 6000; all three arms same harness+settings — a tie within n=30 noise, not a ranking)	accuracy (n=30)	90.4% (bf16: 87.9%, NVFP4 unsloth: 87.9%)
AIME-2026 eval wall-clock (same 240-sample batched workload, RTX PRO 6000 — an aggregate-throughput proxy, not single-stream decode)	duration	2h47m (bf16: 2h37m, NVFP4: 1h02m)
Wikitext-2 perplexity (vLLM prompt-logprobs, 128 chunks x 2048 tok, RTX PRO 6000)	perplexity	7.06 (bf16: 7.02, NVFP4: 7.17)
Weights (vLLM text-only serving; NVFP4 is safetensors size)	GiB	16.68 (bf16: 50.22, NVFP4: 20.47 loaded)
Decode, batch 1 (L4 24 GB, 4096 ctx, CUDA graphs)	tok/s

Single-run measurements; small-n results are noisy estimates. Setup details per row.

How GLQ works

The "Golay/Leech" in the project name refers to the lattice codebooks GLQ also ships (E8 and its higher-dimensional cousins). Code, kernels and quantizer: GLQ on GitHub.

Qwen3.8-27B

[!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, TokenSpeed, etc.

[!Tip] For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates.

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.

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

Benchmark Results

Text Performance

VL Performance

Quickstart

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

Serving Qwen3.8

[!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, vLLM, or TokenSpeed are recommended.

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

API Usage

[!Important] Qwen3.8 models operate in thinking mode by default, generating thinking content signified by <think>\n...</think>\n\n before producing the final response. To disable thinking content and obtain a direct response, refer to the examples here.

[!Tip] We recommend using the following sets of sampling parameters for generation:

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

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

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.

[!Tip] In multi-turn agentic tasks, lower reasoning effort does not always reduce overall task completion time. Although it may produce faster per-turn responses, it can also lead to insufficient analysis, more failures, and repeated retries, which may increase total latency and token consumption.

Chat Completions API

shell
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

python
from openai import OpenAI
# Configured by environment variables
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",
    messages=messages,
    extra_body={
        "chat_template_kwargs": {
            "enable_thinking": True,  # on by default
            "preserve_thinking": True, # on by default
        },
    },
    reasoning_effort="xhigh",  # xhigh by default; supported levels are xhigh, medium, and low
    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

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

Video Input

python
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?"
            }
        ]
    }
]

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

# 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/Qwen3.8-27B",
#     messages=messages,
#     extra_body={
#         "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
#     }, 
# )

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,

python
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/Qwen3.8-27B",
    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)

[!Note] If you are using APIs from Qwen Cloud, in addition to changing model, please use "enable_thinking": False instead of "chat_template_kwargs": {"enable_thinking": False}.

Disable Preserved Thinking

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:

python
from openai import OpenAI

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

[!Note] If you are using APIs from Qwen Cloud, in addition to changing model, please use "preserve_thinking": False directly instead of wrapping it in chat_template_kwargs.

Best Practices

To achieve optimal performance, we recommend the following settings:

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
For supported frameworks, you can adjust the 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.

Citation

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

bibtex
@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}
}

Derivative work of Qwen/Qwen3.8-27B, quantized with GLQ. It inherits the base model's license (apache-2.0) — please respect the base model's terms.

⭐ GLQ on GitHub

Qwen3.8-27B-GLQ-trellis-3inst-4bpw

README

Install

Use with vLLM (recommended)

Use with Transformers

Use with coding agents (pi-code, opencode)

Benchmarks

How GLQ works

Qwen3.8-27B

Qwen3.8 Highlights

Model Overview

Benchmark Results

Text Performance

VL Performance

Quickstart

Serving Qwen3.8

API Usage

Chat Completions API

Text-Only Input

Image Input

Video Input

Instruct (or Non-Thinking) Mode

Disable Preserved Thinking

Best Practices

Citation

Explore FriendliAI today

README

Install

Use with vLLM (recommended)

Use with Transformers

Use with coding agents (pi-code, opencode)

Benchmarks

How GLQ works

Qwen3.8-27B

Qwen3.8 Highlights

Model Overview

Benchmark Results

Text Performance

VL Performance

Quickstart

Serving Qwen3.8

API Usage

Chat Completions API

Text-Only Input

Image Input

Video Input

Instruct (or Non-Thinking) Mode

Disable Preserved Thinking

Best Practices

Citation