Qwen-3-30BA-3B
Emerging6papers using it
2026first seen
The 'Qwen-3-30BA-3B' dataset/benchmark is used to evaluate the performance of LLM inference engines, specifically in the context of matrix execution on CPUs with scalable matrix extensions.
Papers using Qwen-3-30BA-3B (6)
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-TrainingSMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix ExtensionsJudgeRLVR: Judge First, Generate Second for Efficient ReasoningPost-Trained MoE Can Skip Half Experts via Self-DistillationGoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask AlignmentPruning and Distilling Mixture-of-Experts into Dense Language Models