Qwen3.8-Flash-Next-heretic-2-oQ4e-mtp

4-bit oQ4e mixed-precision quantization of trohrbaugh/Qwen3.8-Flash-Next-heretic-2, with Lightning MTP weights preserved.

What oQ4e does

Layers are not quantized uniformly. A sensitivity pass scores each layer's output error against the float baseline, then bits are allocated under a bits-per-weight budget. oQe adds an importance-matrix pass (the idea is borrowed from llama.cpp's imatrix): activation energy is collected per input channel, and each group's affine scale is chosen to minimise sum(importance * (weight - dequantized)^2) rather than plain MSE.

Bit allocation across 652 per-tensor overrides:

The PLE n-gram table is 320M rows x 160 dims (51.2B parameters, ~41% of the model) and is quantized 4-bit at group size 32, giving 5.00 bpw. Group 32 is required, not preferred: rows are 160 wide and the usual group size of 64 does not divide 160, which would leave the table unquantized. The table is gathered by hash id rather than consumed as activations, so it takes ordinary affine quantization with no imatrix weighting.

Calibration

The 21 uncovered expert slots were never routed to by the calibration corpus. They receive a uniform importance vector, which makes the weighted search collapse to standard oQ, so those rows are quantized normally rather than skipped.

Measured throughput

M5 Max, 128 GB, macOS 26.5.2, oMLX 0.6.4 with custom Metal kernels compiled, PLE table on SSD, Lightning MTP enabled. Single request, 12.2k-token code prompt, no prefix-cache hit:

One machine, one workload. Prompt processing on this architecture is sensitive to n-gram locality, so repetitive input (code) measures considerably faster than token-diverse input. Treat these as an upper reference, not a guarantee.

Usage

omlx serve --model-dir <dir>

Enable Lightning MTP in model settings for the generation figure above; it is off by default and worth roughly 1.7x on predictable text. On machines that cannot hold the 30 GB n-gram table in RAM, enable SSD n-gram offload.

---

This is a decensored version of Qwen/Qwen3.8-Flash-Next, made using Heretic (custom fork) v1.3.0+custom

Abliteration parameters

Performance

---

Qwen3.8-Flash-Next

[!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-Flash is the official version based on Qwen3.8-Flash-Next with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-Flash Overview.

As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so. Sustainable progress toward artificial general intelligence (AGI) that benefits everyone demands architectural innovation. Today, we are sharing a concrete step in that direction: Qwen3.8-Flash-Next.

This experimental preview of the architecture that will underpin Qwen4 is built around a fundamental rethinking of how the core components of modern large language models (LLMs) interact at scale.

Highlights

The first open-weight release under this architecture is Qwen3.8-Flash-Next, which introduces:

• Hybrid Attention with QSA: The Gated DeltaNet and Gated Attention pairing has been reworked into Gated DeltaNet and Qwen Sparse Attention (QSA). Rather than selecting individual tokens for processing, QSA operates at the micro-block level. This cuts long-context latency significantly, a critical gain as agentic workloads increasingly dominate real-world usage.
• Gated Residual: Residual streams with normalization are what make deep LLM training manageable. Gated Residual modulates information flowing through widened residual streams via an element-wise, data-dependent read gate and a per-branch scalar write gate. This brings finer-grained expressiveness across layers while preserving training stability and keeping inference overhead low.
• N-gram Embedding: Embeddings provide a unique axis for parameter scaling that requires less computation and is more amenable to offloading than Mixture-of-Experts (MoE). By indexing with short n-grams, this approach makes parameter scaling highly efficient for memory-constrained accelerators without sacrificing quality.
• Tailored Training Recipe: The Muon and AdamW optimizers are applied to specific weight categories to maximize efficiency. Guided by refitted scaling laws, we eliminate traditional batch-size warmups and start directly at the target batch size, substantially reducing total optimizer steps while safely supporting larger learning rates for robust convergence.

For more details, please refer to our blog post Qwen3.8-Flash-Next and the technical report.

We are excited to embark on this next chapter with you and welcome your feedback as we build what comes next.

Model Overview

• Type: Causal Language Model with Vision Encoder
• Training Stage: Pre-training & Post-training
• Language Model
  • Number of Parameters: 125B with 6B activated, plus 51B n-gram embedding and 4B MTP
  • Hidden Dimension: 2560
  • Token Embedding: 248320 (Padded)
  • N-gram Embedding: 20,000,000 (bigrams/trigrams at layer 2)
  • Number of Layers: 48
  • Hidden Layout: 12 × (3 × (Gated DeltaNet → MoE) → 1 × (Qwen Sparse Attention → MoE))
  • Gated DeltaNet:
    • Number of Linear Attention Heads: 48 for V and 16 for QK
    • Head Dimension: 128
  • Qwen Sparse Attention:
    • Number of Attention Heads: 24 for Q and 2 for KV
    • Head Dimension: 256
    • Rotary Position Embedding Dimension: 64
    • Indexer Structure: MQA with 4 Query Heads and 1 Shared Key Head
    • Indexer Head Dimension: 128
    • Budget: 512 blocks or 2048 tokens
  • Mixture Of Experts
    • Number of Experts: 512
    • Number of Activated Experts: 10 Routed + 1 Shared
    • Expert Intermediate Dimension: 640
  • Gated Residual:
    • Number of Branches: 4
    • Bottleneck Rank: 320
  • LM Output: 248320 (Padded)
  • MTP: 1 layer, trained with multi-steps
• Context Length: 262,144 natively and extensible up to 1,000,000 tokens.

Benchmark Results

Language

1. DeepSWE 1.1: evaluated with the Claude Code and mini-SWE-agent harnesses, temp=1.0, top_p=0.95, 256K context window. We report the highest score across the two harnesses; notably, Qwen3.8-Flash-Next performs best on mini-SWE-agent.
2. SWE-bench Pro: except for Claude-Opus-4.6 (Max), for which we report the officially published score, all models are evaluated with the Claude Code harness, temp=1.0, top_p=0.95, 256K context window. Problematic tasks were corrected and all baseline models were re-evaluated on the refined benchmark.
3. SWE-bench Multilingual: evaluated with the mini-SWE-agent harness, temp=1.0, top_p=0.95, 256K context window.
4. 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.
5. CoWorkBench: an in-house cowork benchmark for evaluating long-horizon office and productivity agent 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 (--): scores are not yet available or are not applicable.

Vision Language

1. ClawEval-MM: scores are reported as "pass@3 / average score". Pass@3 measures the percentage passed in at least one of three trials, and the average score is the mean score across the three trials.
2. RecreationBench: an in-house long-horizon application-recreation benchmark for evaluating hybrid-agent abilities spanning five platforms — desktop (Ubuntu, macOS, Windows), mobile (Android) and web.
3. OSWorld 2.0: scores are reported as "binary / partial". The binary score is the percentage of tasks that receive the full task reward, while the partial score aggregates the partial rewards obtained across all tasks.
4. Vision2Web: scores are reported as the average over the frontend, webpage and website categories, using the Claude Code harness and judged by gpt-5.4-2026-03-05.
5. MathVision, CharXiv (RQ): scores are reported as "without CI / with CI". A small number of incorrect ground-truth annotations in MathVision were corrected after manual verification. 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.
6. The best result in each row is shown in bold.
7. Empty cells (--) indicate scores not yet available or not applicable.

Quickstart

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

Serving Qwen3.8-Flash-Next

[!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.

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

• SGLang: Qwen3.8-Flash-Next Cookbook
• vLLM: Qwen3.8-Flash-Next Recipe
• TokenSpeed: Qwen3.8-Flash-Next Recipe

API Usage

[!Important] Qwen3.8-Flash-Next 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.

[!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.

[!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.

Qwen3.8-Flash-Next supports controlling thinking behavior via enable_thinking, preserve_thinking, and reasoning_effort.

Chat Completions API

The Chat Completions API can be used with most inference frameworks, as well as Qwen Cloud. 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"

Text-Only Input

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-Flash-Next",
    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

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-Flash-Next",
    messages=messages,
)
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?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-Flash-Next",
    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-Flash-Next",
#     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-Flash-Next 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
# 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-Flash-Next",
    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-Flash-Next 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

# Configured by environment variables
client = OpenAI()
messages = [...]
chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.8-Flash-Next",
    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:

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

   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.

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

3. Processing Ultra-Long Texts: Qwen3.8-Flash-Next 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., 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  
     

   [!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.

4. 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.

@techreport{qwen2026design,
    title       = {On the Design of {Qwen3.8-Next} Architecture: Evaluation, Efficiency, and Training Stability},
    author      = {{Qwen Team}},
    institution = {Alibaba Group},
    month       = {August},
    year        = {2026}
}

@misc{qwen3.8flashnext,
    title  = {{Qwen3.8-Flash-Next}: A New Architecture, Towards Ultimate Cost-Efficiency},
    author = {{Qwen Team}},
    month  = {August},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.8-flash-next}
}