Marketplace · Text & chat
Qwen/Qwen3.8-Flash-Next
Call Qwen/Qwen3.8-Flash-Next through one OpenAI-compatible API, served by independent machines at prices their owners set. There's no host for it on the grid at this moment (last live 7 Sep 2026) — so the next machine that loads it serves every request for it.
The grid is one machine short.
If your machine already runs open models, it can most likely serve Qwen/Qwen3.8-Flash-Next too. Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid.
- Install the connector. One command on the machine that runs your models. It dials out over an encrypted link — no ports to open. The connector
- Load
Qwen/Qwen3.8-Flash-Next. It has run here on vllm; any supported engine works. The platform benchmarks it on your hardware first. - Set your price. Developers see your price beside the speed your machine measures.
- Get paid when it's called. Switch it off whenever you like. How hosting works
About Qwen/Qwen3.8-Flash-Next.
- Type: Text & chat
- Context window: up to 262,144 tokens
- Runs on: vllm
- First on the grid: 7 Sep 2026
- Hosts serving it now: 0
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
model="Qwen/Qwen3.8-Flash-Next",
messages=[{"role": "user", "content": "Hello"}],
)Qwen/Qwen3.8-Flash-Next in detail.
> [!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.
- Published by
- Qwen
- Parameters
- 180B
- Format
- transformers
- Architecture
- qwen4_exp
- Licence
- qwen-community-1.0
- Task
- image text to text
- Library
- transformers
- First published
- 24 Aug 2026
- Last updated
- 7 Nov 2026
- Downloads (30 days)
- 3.6 million on Hugging Face
- Likes
- 6,848
qwen4_exp image-text-to-text
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
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.
Read the rest of the model card
Benchmark Results
Language
Qwen3.8-Flash-NextQwen3.8-27BQwen3.7-PlusDeepSeek-V4-Flash-0731Claude-Opus-4.6 (Max)
Params
125B 27B 397B 284B --
Activated params
6B 27B 17B 13B --
N-gram embedding params
51B -- -- -- --
Coding
Agentic codingDeepSWE 1.1 58.7 42.2 16.5 54.4 --
Agentic codingSWE-bench Pro 62.5 61.7 55.8 56.0 53.4
Multilingual software engineeringSWE-bench Multilingual 81.0 73.8 75.8 -- 77.5
Repo-level code generationNL2Repo-Bench 48.1 42.3 41.1 54.2 47.6
Agent
Long-horizon office workCoWorkBench 73.9 70.7 65.1 45.1 68.2
Professional job tasksJobBench 55.7 33.4 27.6 41.3 36.6
Frontier agentic tasksAgents' Last Exam [email protected] [email protected] [email protected] [email protected] --
Real-world tool useToolathlon Verified (Pass@1) 73.5 67.1 50.6 70.3 --
General
Instruction followingIFBench 81.3 79.5 79.1 79.2 62.5
Scientific reasoningGPQA Diamond 91.7 89.2 90.3 90.8 91.3
Multidisciplinary reasoningHLE 35.9 30.8 34.7 33.8 40.0
Competitive codingLiveCodeBench v6 91.9 90.3 89.6 90.6 88.8
- 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.
- 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.
- SWE-bench Multilingual: evaluated with the mini-SWE-agent harness, temp=1.0, top_p=0.95, 256K context window.
- 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.
- 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.
- HLE: judged by GPT-4o.
- The best result in each row is shown in bold.
- Empty cells (--): scores are not yet available or are not applicable.
Vision Language
Qwen3.8-Flash-NextQwen3.8-27BQwen3.7-PlusClaude-Opus-4.6 (Max)
Agentic Multimodal Intelligence
Multimodal tool useClawEval-MM [email protected] [email protected] [email protected] [email protected]
Application recreationRecreationBench 49.9 47.1 30.2 --
Mobile useAndroidWorld 84.5 81.9 81.0 62.0
Computer useOSWorld 2.0 Binary19.4Partial52.3 Binary19.4Partial48.0 Binary2.8Partial21.5 --
Visual web developmentVision2Web 64.0 62.9 42.1 --
General Multimodal Intelligence
Embodied intelligenceERQA 72.3 65.5 69.8 40.8
Long video understandingLVBench 76.6 72.4 76.2 63.0
Real-world perceptionRealWorldQA 88.5 85.9 86.9 73.9
Visual math problem solvingMathVision Without CI90.6With CI95.7 Without CI90.0With CI94.6 Without CI90.3With CI88.7 Without CI65.5
Scientific chart analysisCharXiv (RQ) Without CI84.6With CI90.6 Without CI83.7With CI90.2 Without CI85.8With CI85.9 Without CI66.0
- 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.
- 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.
- 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.
- 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.
- 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.
- The best result in each row is shown in bold.
- 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 \n...\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=1.0Please 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 changingmodel, please use"enable_thinking": Falseinstead 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 changingmodel, please use"preserve_thinking": Falsedirectly instead of wrapping it inchat_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 presence_penalty parameter between 0 and 2 to reduce endless repetition. However, usi
Sources: Qwen/Qwen3.8-Flash-Next on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Live now instead.
Similar text & chat models with hosts serving them right now.
- qwen2.5:0.5b — from £0.009 per 1M output tokens · 5 hosts
- functiongemma:latest — from £0.015 per 1M output tokens · 4 hosts
- glm-ocr:latest — from £0.06 per 1M output tokens · 3 hosts
- granite4.2:3b — from £0.06 per 1M output tokens · 3 hosts
- lfm3:latest — from £0.043 per 1M output tokens · 3 hosts
- llama-guard3:1b — from £0.018 per 1M output tokens · 3 hosts
Questions about Qwen/Qwen3.8-Flash-Next.
Can I use Qwen/Qwen3.8-Flash-Next through an API?
Yes. Inpherio serves Qwen/Qwen3.8-Flash-Next through one OpenAI-compatible API whenever a host on the grid is running it — the code on this page works unchanged. With no host right now, a call returns a "not available on any node" error and is never charged, and similar models are live on the marketplace.
How do I host Qwen/Qwen3.8-Flash-Next and get paid?
Install the Inpherio connector on the machine that runs your models, load Qwen/Qwen3.8-Flash-Next in a supported engine, and set a price. The platform benchmarks it on your hardware, then requests for it reach your machine. Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid.
Why is Qwen/Qwen3.8-Flash-Next not being served right now?
Hosts on Inpherio are independent machines that come and go. It was last live on 7 Sep 2026. When a host loads it again, this page shows live prices and measured speeds.