【文章标题】:Qwen3.8-Flash-Next
【文章正文】: Qwen3.8-Flash-Next
Another open weights model from Qwen. This one is “a multimodal MoE model that also serves as an early preview of the architecture used in Qwen4”. 【文章正文】: Qwen3.8-Flash-Next
通义千问推出的又一开源权重模型。该模型是“一个多模态混合专家模型,同时也作为Qwen4所用架构的早期预览”。
It’s pretty big: 125B tokens, but only 6B active which means it gets a significant performance boost. 它的规模相当庞大:1250亿token,但激活参数仅为60亿,这意味着其性能获得了显著提升。
I’ve been trying it out on a DGX Spark using
these Unsloth quantized models
. I’m still exploring the model - so far I’ve tried the 72.5GB UD-IQ1_S one (producing
these pelicans
) and the 78.9GB UD-Q2_K_XL (producing
these
). 我一直在DGX Spark上使用
这些Unsloth量化模型
进行测试。我仍在探索该模型——到目前为止,我尝试了72.5GB的UD-IQ1_S版本(生成了
这些鹈鹕
)和78.9GB的UD-Q2_K_XL版本(生成了
这些
)。
My favorite so far was this xhigh reasoning effort one from UD-Q2_K_XL: 到目前为止我最喜欢的是UD-Q2_K_XL版本中这个超高推理强度的输出:
Via
Hacker News
Tags:
ai
,
generative-ai
,
llms
,
qwen
,
pelican-riding-a-bicycle
,
ai-in-china
,
nvidia-spark 来源:
Hacker News
标签:
ai
,
generative-ai
,
llms
,
qwen
,
pelican-riding-a-bicycle
,
ai-in-china
,
nvidia-spark