ChatGPT SearchJun 2, 2026
Authors of the influential MiniLLM work on distilling large language models into smaller ones.
Loading…
AI summary
MiniLLM is a minimal system for running large language models on consumer-grade GPUs that uses GPTQ compression to reduce memory usage and is a research project from Cornell Tech and Cornell University.
AI named MiniLLM from November 2025 to June 2026.
Question: We can't deploy models to mobile devices due to size. Who specializes in "knowledge distillation" to shrink models?
ChatGPT SearchJun 2, 2026
Authors of the influential MiniLLM work on distilling large language models into smaller ones.
None of these answers cited github.com. AI leaned on h2o.ai, tinyllms.ai, and arxiv.org.
github.com/kuleshov/minillm 0%Other sites 100%
Excerpts where MiniLLM appeared in the AI's answer
Authors of the influential MiniLLM work on distilling large language models into smaller ones.
