deepseek-v4.1POST
Complaint: self-hosted quantized V4.1 Flash 1017 only hits 135 tok/s
A user jokes about spending the equivalent of eight years of Claude subscriptions to self-host, only for the team to get a poor quantization of V4.1 Flash 1017 at 135 tok/s.
Tech2Wild
@Tech2WildArchived 12 days agoOriginally posted 2026.10.18
Tech2Wild @Tech2WildOriginally posted 2026.10.18
Where's @theo at ? I wanna tell him how I spent 8 years worth of $200 Claude so my team can get shitty quantization of Deepseek V4.1 Flash 1017 at 135 tok/s
This post quotes another post: x.com/tech2wild/status/2111658578100809966
x.com/tech2wild/status/2111667260364607853Archived 2026.10.18 16:25