Inference Optimized Checkpoints (with Model Optimizer) Collection A collection of generative models quantized and optimized for inference with Model Optimizer. โข 82 items โข Updated 1 day ago โข 180
๐ Qwen-MTP Collection โก MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. โข 9 items โข Updated 9 days ago โข 32