Unknown family

User benchmarks an unnamed MoE model on an NVIDIA DGX Spark, reaching 102.88 tok/s decode with MTP speculative decoding (NEXTN, steps=3, topk=1, draft_tokens=4) versus a 36.09 tok/s baseline. The setup stacks three optimizations: a Humming MXFP4 MoE backend, online FP8 LM head quantization, and MTP speculation. Each step is measured: Humming MoE alone gives 39.45 tok/s (+9.3%), adding the FP8 LM head gives 43.94 tok/s (+21.7%), and MTP brings it to 102.88 tok/s (+185.1%).