DeepSeek-V4-Flash Called a 'Monster' Model, Tops OpenRouter Usage

natolambert · x · 2026-08-05

AI researcher Nathan Lambert reshared and commented that the adoption numbers of DeepSeek V4 Flash are insane and underrated. He noted that the new version scores the same as GLM 5.2, making it a 'total monster' that will be used extensively.

According to Artifacts Hub data, the model features a 284B parameter (13B active) MoE architecture. It has not only accumulated over 9.4 million all-time downloads on Hugging Face but also became the top model on OpenRouter, processing an average of 1 trillion tokens per day.

Related event: DeepSeek V4 Flash Tops OpenRouter, Costs 1% of Rivals(14 posts)→

Original post →

More from Models

Models channel →