ModelScope(@ModelScope2022):DeepSeek-V4.1-Flash just landed on ModelScope! 🐋 A 552B multimodal MoE with 1M context that activates only 8B params on prefill and 16B on decode. MIT license. 🤖 https://t.co/P37rtuLoaQ 🏆 New SOTA on DeepSWE v1.1 (74.2), Terminal-Bench 2.1 (90.6), CyberGym (88.1), and Agent's Last Exam (31.8), beating Claude Opus-5.0 and GPT-5.6 Sol. ⚙️ A Causal Encoder-Decoder design built for input-heavy agent work: read huge codebases with 8B active, decode with 16B. 📉 Global KV cache compressed to 890 bytes per token, 4x smaller than DeepSeek-V4-Flash and 437x smaller than V1, making 1M context cheap to serve. 🎛️ Reasoning effort is a continuous dial from 1 to 100, not three presets. Trade cost for accuracy as finely as you need.

ModelScope@ModelScope2022

2026.09.10 07:26

DeepSeek-V4.1-Flash just landed on ModelScope! 🐋 A 552B multimodal MoE with 1M context that activates only 8B params on prefill and 16B on decode. MIT license. 🤖 🏆 New SOTA on DeepSWE v1.1 (74.2), Terminal-Bench 2.1 (90.6), CyberGym (88.1), and Agent's Last Exam (31.8), beating Claude Opus-5.0 and GPT-5.6 Sol. ⚙️ A Causal Encoder-Decoder design built for input-heavy agent work: read huge codebases with 8B active, decode with 16B. 📉 Global KV cache compressed to 890 bytes per token, 4x smaller than DeepSeek-V4-Flash and 437x smaller than V1, making 1M context cheap to serve. 🎛️ Reasoning effort is a continuous dial from 1 to 100, not three presets. Trade cost for accuracy as finely as you need.