Comment by jchw
1 day ago
Am I wrong to assume that large MoE models are likely the point anyway? Seems like this card would love DeepSeek V4.1 Flash.
1 day ago
Am I wrong to assume that large MoE models are likely the point anyway? Seems like this card would love DeepSeek V4.1 Flash.
No comments yet
Contribute on Hacker News ↗