Tag

Qwen3-14B

Every Qwen3-14B story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.

3 items · 3 issues

Beats AI & ML

Often covered with Qwen3-4B 3 vLLM 2 NVIDIA H200 2 Reinforcement Learning (RL) 1 Qwen3-8B 1

Week 40 · 2026

Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Researchers have developed FlyBy, a framework that allows small language models to overcome knowledge limitations by selectively querying stronger external models. This approach optimizes test-time computation by distinguishing between problems solvable through more thought and those requiring new information.

AI & ML HuggingFace Papers Source ↗

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This technical report examines the efficacy of using Random Attention for KV cache eviction to optimize LLM inference throughput. The study shows that this method significantly boosts tokens per second in high-concurrency scenarios without sacrificing model accuracy.

AI & ML HuggingFace Papers Source ↗

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This technical report examines the efficacy of using Random Attention for KV cache eviction to optimize LLM inference throughput. The study shows that this method significantly boosts tokens per second in high-concurrency scenarios without sacrificing model accuracy.

AI & ML HuggingFace Papers Source ↗