NVFP4 Collection Dynamic Unsloth NVFP4 Quants. Faster and more accurate. โข 11 items โข Updated 2 days ago โข 65
Inference Optimized Checkpoints (with Model Optimizer) Collection A collection of generative models quantized and optimized for inference with Model Optimizer. โข 91 items โข Updated about 24 hours ago โข 185
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 Jun 29 โข 36