Open-Weight LLM Models — Live Ranking, Benchmarks & Specs
Explore, filter and compare open-weight language models with live specs, benchmarks and license data
Hy4 preview
Tencent
MoE (78 layers) with Gated DeepSeek Sparse Attention (Gated DSA) + IndexCache cross-layer sparse index reuse, iHC (identity Hyper-Connections) residual streams, 1 native MTP layer (10B total / 0.7B active) for speculative decoding
Hunyuan
Apache License 2.0
Openness Score
1.0
Hy3
Tencent
MoE (80 layers + 1 MTP) with GQA (64 heads/8 KV) + QK-Norm, 192 experts top-8 + 1 shared expert, sigmoid router with expert bias
Hunyuan
Apache License 2.0
Openness Score
1.0