{"version":"1.0","workflow_uuid":"80f47f36-54af-11f1-9bc6-00163e2b0d79","workflow_title":"AutoGPTQ — Easy-to-Use GPTQ Quantization for Large Language Models","install_contract":{"version":"1.0","installReady":false,"title":"AutoGPTQ — Easy-to-Use GPTQ Quantization for Large Language Models","summary":"AutoGPTQ is a Python library that simplifies GPTQ-based weight quantization for large language models. It reduces model sizes by 4x with minimal accuracy loss, making it possible to run large models on consumer GPUs for inference.","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/asset-80f47f36","sourceUrl":"https://github.com/AutoGPTQ/AutoGPTQ","intendedFor":[],"firstActions":[],"agentFirstSteps":[],"targetPaths":[],"verification":[],"startingPoints":[],"example":"","successOutcome":"","boundaries":[],"askUserIf":["the current workspace stack cannot be matched to a safe upstream template","the target path is not the project root, or an existing file should be merged instead of overwritten"]}}