🚀 Keye-VL-2.0-30B-A3B released — fully open.
The first VLM to land DSA (DeepSeek Sparse Attention) in production — nearly lossless reasoning over 256K ultra-long context.
30B params. Fully open. 🤗
🧵👇
🚀 Keye-VL-2.0-30B-A3B released — fully open.
The first VLM to land DSA (DeepSeek Sparse Attention) in production — nearly lossless reasoning over 256K ultra-long context.
30B params. Fully open. 🤗
🧵👇
▸ Tops video benchmarks at its scale
▸ Outperforms Qwen3-VL-235B on LongVideoBench (74.1)
▸ First Keye base model with built-in Agent: Code · Tool · Search