test-models - a inference-optimization Collection

inference-optimization 's Collections

HIGGS-per-tensor

test-models

updated about 6 hours ago

inference-optimization/Qwen3-Next-80B-A3B-Instruct-MTP-ultrachat-epoch3

2B • Updated Mar 19 • 8
inference-optimization/Qwen3-Next-80B-A3B-Instruct-MTP-ultrachat-epoch1

2B • Updated Mar 19 • 1
inference-optimization/Qwen3-Next-80B-A3B-Instruct-MTP-ultrachat-epoch2

2B • Updated Mar 19 • 4
inference-optimization/Qwen3-Next-80B-A3B-Instruct-GSM8K-MTP-finetuned

81B • Updated Mar 25 • 42

Note Qwen3-Next-80B with GSM8K-finetuned MTP head (+22.5% acceptance rate). Generated using speculators.