DGrid AI(@dgrid_ai):🔥 DeepSeek-V4.1-Flash from @deepseek_ai is now on DGrid. Smarter, faster, more efficient — the smallest model in DeepSeek’s new architecture family, with native visual understanding. ✅ 552B MoE, with just 8B active on input and 16B on output ✅ Native multimodal support ✅ Benchmark results ahead of flagship models, including DeepSeek-V4-Pro ✅ Smaller KV cache: 1/4 the HBM and 1/8 the SSD vs the previous generation Try it now: https://t.co/8911k8bOkU #DGrid #AI

2026.09.11 01:25

🔥 DeepSeek-V4.1-Flash from @deepseek_ai is now on DGrid. Smarter, faster, more efficient — the smallest model in DeepSeek’s new architecture family, with native visual understanding. ✅ 552B MoE, with just 8B active on input and 16B on output ✅ Native multimodal support ✅ Benchmark results ahead of flagship models, including DeepSeek-V4-Pro ✅ Smaller KV cache: 1/4 the HBM and 1/8 the SSD vs the previous generation Try it now: #DGrid# #AI#

DeepSeek@deepseek_ai

2026.09.10 06:10

🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6