Open-Weight LLM Models — Live Ranking, Benchmarks & Specs
Explore, filter and compare open-weight language models with live specs, benchmarks and license data
Edge0-120B-NVFP4
Edge0
Latent sparse MoE transformer, hybrid attention (full every 4 layers + sparse indexer), 512 experts/layer (10 routed + 1 shared), expert streaming from host RAM/SSD
Edge0
Edge0 Community Model License 1.0
Openness Score
0.5
Edge0-145B-NVFP4
Edge0
Latent sparse MoE transformer, hybrid attention (full every 4 layers + sparse indexer), 512 experts/layer (10 routed + 1 shared), expert streaming from host RAM/SSD
Edge0
Edge0 Community Model License 1.0
Openness Score
0.5