Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 21 items • Updated 1 day ago • 80
Qwen3 DWQ Quants Collection High-quality 4-bit quants of the Qwen3 model family. • 8 items • Updated Jul 11, 2025 • 7
Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 • 11 items • Updated 11 days ago • 550