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)→
More from Models
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
- Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16