Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
AWQgithub.comAWQ is an activation-aware weight quantization method for compressing and accelerating large language models (LLMs) to INT3/INT4 precision. It provides efficient CUDA kernels and a TinyChat interface for running LLMs on resource-constrained edge devices like NVIDIA Jetson Orin.
Parse Score
Domain | Citations |
|---|---|
| 2 | |
| 1 | |
| 1 | |
| 1 | |
| 1 |
