ai/qwen3.8-flash-next
Qwen3.8-Flash-Next是Qwen4架构的实验预览版开源大语言模型镜像，具备高效长上下文处理能力，适用于代码生成、智能代理等场景，可通过llama.cpp或Unsloth Desktop运行。
让 AI 帮你使用轩辕镜像？ · 展开查看说明 · 点击收起说明
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具，协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题，请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这段话即可：
请先阅读并遵守：https://xuanyuan.cloud/agents.md
未读文档前不要生成 pull 命令或排错方案。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式，不推荐豆包 AI；Cursor 等编辑器可在对话 @ 该链接，或加入 User Rules。 若 AI 无法访问外链，可 打开说明文档 复制全文粘贴。文档会随站点更新，复制内容可能过期，建议定期检查。
Read our How to https://unsloth.ai/docs/models/qwen3.8-next
https://unsloth.ai/docs/basics/dynamic-3.0-ggufs achieves superior accuracy & outperforms other leading quants.
https://github.com/unslothai/unsloth/
https://github.com/unslothai/unsloth/https://github.com/unslothai/unsloth/https://qwen.ai/blog?id=qwen3.8-flash-next and https://github.com/QwenLM/Qwen3.8-Flash-Next/blob/main/tech_report.pdf.
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
| Qwen3.8-Flash-Next | Qwen3.8-27B | Qwen3.7-Plus | DeepSeek-V4-Flash-0731 | Claude-Opus-4.6 (Max) | |
|---|---|---|---|---|---|
# Params | 125B | 27B | 397B | 284B | -- |
# Activated params | 6B | 27B | 17B | 13B | -- |
# N-gram embedding params | 51B | -- | -- | -- | -- |
| Coding | |||||
Agentic coding DeepSWE 1.1 | 58.7 | 42.2 | 16.5 | 54.4 | -- |
Agentic coding SWE-bench Pro | 62.5 | 61.7 | 55.8 | 56.0 | 53.4 |
Multilingual software engineering SWE-bench Multilingual | 81.0 | 73.8 | 75.8 | -- | 77.5 |
Repo-level code generation NL2Repo-Bench | 48.1 | 42.3 | 41.1 | 54.2 | 47.6 |
| Agent | |||||
Long-horizon office work CoWorkBench | 73.9 | 70.7 | 65.1 | 45.1 | 68.2 |
Professional job tasks JobBench | 55.7 | 33.4 | 27.6 | 41.3 | 36.6 |
Frontier agentic tasks Agents' Last Exam | Pass@1 24.3 Score 51.2 | Pass@1 20.4 Score 42.9 | Pass@1 13.2 Score 33.6 | Pass@1 25.2 Score -- | -- |
Real-world tool use Toolathlon Verified (Pass@1) | 73.5 | 67.1 | 50.6 | 70.3 | -- |
| General | |||||
Instruction following IFB
…(truncated — see the full README on HuggingFace) | |||||
镜像拉取方式
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本，请访问 标签列表页面。
轩辕镜像加速拉取命令点我查看更多 qwen3.8-flash-next 镜像标签
docker model pull docker.xuanyuan.run/ai/qwen3.8-flash-next:<标签>
DockerHub 原生拉取命令
docker model pull ai/qwen3.8-flash-next:<标签>
镜像拉取常见问题
功能
错误码
用户好评
来自真实用户的反馈，见证轩辕镜像的优质服务
oldzhang
运维工程师
Linux服务器
5
"Docker访问体验非常流畅，大镜像也能快速完成下载。"