AIDigitalOcean2 months ago
DeepSeek, MiniMax, Qwen hit DigitalOcean Serverless Inference
7 min read
DigitalOcean launched DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B on Serverless Inference. DeepSeek V3.2 and Qwen 3.5 397B achieved the fastest output speed across all providers tested by Artificial Analysis. DeepSeek V3.2 delivers 230 output tokens per second with sub-1-second Time-to-First-Token for 10,000 input tokens.
Level
Hype check
Tap to vote and see what everyone thinks.
