Pinned Tweet
卧槽?!
本地部署成功。
这速度太爽了!
最近开源的推理框架Strata的爆火,
让125B参数的Qwen-3.8-Flash运行在家用GPU上。
这里分享一个如何将模型部署到本地电脑的教程。
这个教程包含:
- 文档
- 视频
- MTP 加速
最厉害的是部署 无审查 版。
对,你没有看错,无审查版本。
传送门:xgdn.com/90.html
Strata新版本体验了👏👏!
升级了:
Strata:0.2.16
Strata Engine:0.1.62
模型: Qwen3.8-Flash-Unsloth-UD-IQ4_XS_V3.1
DSH工具调用,
和上次0.2.13对比
直观感觉:
- 解码和Prefill速度降低了👇
- 专家比之前多了
新特点:
- 自主研发新的引擎代码
- 不使用 ggml 和 llama.cpp 矩阵内核
卧槽?!卧槽?!
升级了:
Strata:0.2.13
Strata Engine:0.1.59
模型: Qwen3.8-Flash-Unsloth-UD-IQ4_XS_V3.1
DSH工具调用,
和上次0.2.12对比
直观感觉:速度又又提升了!
不断进步啊!
3
19
5,405
回归有望!
就看董事会的决定了!
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me.
I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA.
I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation.
Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO.
Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours.
Jensen
151
马上发布了!
期待开放权重!
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery!
Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window.
Highlights:
- Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation.
- Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables.
- Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery.
- $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%.
The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder.
Start building today! 🚀
- Blog: qwen.ai/blog?id=qwen4-max
- API: qwencloud.com/models/qwen4-m…
- Token Plan: qwencloud.com/pricing/token-…
More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
1
209
在本地模型 + DSH的配合下,
终于将Agent开发成DSH的工作台,
后续创作视频时方便了不少!
DSH确实👍👍👍
昨天花了些时间从Hermes切到DSH,
目前DSH的版本0.2.1-rc.5
我是用Hermes的感受:
- 实力还是得肯定的
主要说为什么切换:
- 更新太频繁,一天好多次提交,右下角蓝色几乎没断过
- 体积太大,需要通过源码来安装
- 内存占用不少,也许是Electron的通病
-其他:程序崩溃,安装更新经常失败(可能是网络原因)
其实让我决定切换的主要原因还是体积,
将skill和agent去除之外,
我删掉的数据大概有11G,
硬盘一下就腾出了11G啊!
昨天弄完DSH的环境,
一直都是用:标准模式。
今天开始:创造模式了!
后续,可以好好探究下DSH了!
3
6
838
有幸可以尽微薄之力,
希望老黄一切都好好的!
华人之光!
已经签名!
阅读Stand with Jensen的信件并考虑加上您的名字。 #standwithjensen #bringjensenback standwithjensen.com/
看到这个消息,
第一,有点不敢信。
第二,不可思议!
NVIDIA announces CEO transition. Read the release: nvidianews.nvidia.com/news/n…
1
173
终于要来了!!
期待Qwen4-Flash版本!!!
Qwen4 is coming.
Deeper knowledge. Richer world understanding. Stronger coding and agentic capabilities.
Built for real-world tasks — from complex coding and knowledge work to front-end builds and professional software workflows.
Qwen4-Max is now in preview on Alibaba’s Token Plan. You can also get early access to the new model on QwenWork, Qoder, Qwen APP, and QwenStudio.
Put it to the test on a real problem. Show us what you build. 👀
Token Plan: qwencloud.com/pricing/token-…
2
360
终于看到一个立场不一样的!
支持!!!
全网羞辱黄仁勋,适可而止吧。
从我做起。从今以后,不再关注此事,直到调查结果出来。
再次重申我的立场:
- 黄仁勋是华人少有的领袖,带领 Nvidia 成为市值第一
- 私生活问题我不关心,是他的个人选择
- 是否叛国要看调查结果,目前持乐观态度
- Nvidia 仍是一家伟大的公司,值得长期投资
- 经济学人之类的污糟猫,自己去学做人吧
老黄加油,祝早日渡过难关 💪!
@JensenHuang
1
222
卧槽?!
太能整活了!
一觉醒来!
MiniMax发布了:
图片生成模型:MiniMax H3-Image
- 4K 图像生成只需 10 秒!
- 1600 万像素分辨率。
- 惊艳的真实感。
- 精准的提示词遵循与编辑。
- 最多 16 张参考图像。
- 全部只需 10 秒。
- 而且它是开源权重的。
这视频创作搭配自家的图形视频模型,
岂不是要起飞了!
1
2
1,120
不得不说啊!
遇到DSH会话中输出截断的问题,
然后让模型自己分析并解决,
得益于:
推理引擎:Strata-0.2.12
模型: Qwen-Flash-Unsloth-UD-IQ4_XS_V3.1
果然不负所望,
分析过程,
解决方案。
一气呵成!
这效率可以!
升级了:
Strata:0.2.12
Strata Engine:0.1.58
直观感觉:
速度好像又提升了!
DSH工具调用时,
“吐字”快了点!
任务完成时间缩短了!
当然我没有具体量化!
速度快!
准确率也高了!
一方面Qwen-3.8-Flash-Next本身的实力不俗
另一方面,Dynamic V3.1的算法确实也立功不少!
期待Qwen4.0-Flash啦!!!
Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.
Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.
Results: 50% fewer tokens + 15% higher accuracy vs same size quants.
GGUF: huggingface.co/unsloth/Qwen3…
3
19
4,239
感谢大模型量化一哥 -- Unsloth官方@UnslothAI的赞👏👏!
继续加油!
我的效率也得跟上啊!
昨天更新的Unsloth Dynamic v3.1版本的,
Qwen3.8-Flash-Next-UD-IQ4_XS部署成功了!
效果如下:
推理引擎:Strata 0.2.11
模型:unsloth/Qwen3.8-Flash-Next-UD-IQ4_XS V3.1
测试:three.js完成鹈鹕骑车
不足:模型不是无审查,很多问题直接拒绝!😓😓
左图DSH调用模型的速度👇
这速度干活一点毛病没有!
右图是调用它完成的鹈鹕骑车🤣🤣🤣
6
1,094
我的效率也得跟上啊!
昨天更新的Unsloth Dynamic v3.1版本的,
Qwen3.8-Flash-Next-UD-IQ4_XS部署成功了!
效果如下:
推理引擎:Strata 0.2.11
模型:unsloth/Qwen3.8-Flash-Next-UD-IQ4_XS V3.1
测试:three.js完成鹈鹕骑车
不足:模型不是无审查,很多问题直接拒绝!😓😓
左图DSH调用模型的速度👇
这速度干活一点毛病没有!
右图是调用它完成的鹈鹕骑车🤣🤣🤣
我勒个去?!
划重点:
支持新的Unsloth Qwen-3.8-Flash-Next量化版本
这效率太高了!
早上刚转发了Unsloth Dynamic V3.1的新量化版本。
晚上Strata新版本就支持了👍👍👍
应该就是Dynamic v3.1的量化版本。
传送门:
huggingface.co/unsloth/Qwen3…
























