{"adoption": {"forks": 453, "observed_at": "2026-08-28T04:07:41.648654+00:00", "stars": 3073}, "canonical_url": "https://ross.abutalabs.com/products/gptq-for-llama", "card": {"archived": false, "artifact_type": "library", "description": "4 bits quantization of LLaMA using GPTQ", "domain": ["large-language-models", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["qwopqwop200/GPTQ-for-LLaMa"], "name": "qwopqwop200/GPTQ-for-LLaMa", "platform": ["python"], "pushed_at": "2024-07-13T04:45:28+00:00", "repo": "qwopqwop200/GPTQ-for-LLaMa", "stars": 3073, "tags": ["quantization", "gptq", "llama", "4-bit", "model-compression", "triton", "linux", "gpu"], "topics": [], "urls": [], "use_cases": ["quantize llama models to 4 bits", "run llama 7b on a smaller gpu", "compress large language model checkpoints", "reduce vram usage for llama inference", "convert llama weights with gptq"], "what_it_is": "A Python library that applies GPTQ 4-bit weight quantization to LLaMA large language models, drastically reducing memory usage and checkpoint size. It is now superseded by AutoGPTQ, which the author recommends instead.", "when_to_avoid": ["you want an actively maintained or feature-rich quantization toolkit - use AutoGPTQ instead", "you are on Windows without WSL2, since Triton support is Linux-only", "you need the fastest possible quantized inference kernels"], "when_to_choose": ["you specifically need the original GPTQ-for-LLaMA implementation or its benchmarks", "you are on Linux and want a simple standalone quantization script for LLaMA"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gptq-for-llama", "repo": "qwopqwop200/GPTQ-for-LLaMa", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.648654+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:27:57.305309+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "057de12155c015c0ae1b2edc0975c2acb8f6a58711ad9b80a9698c5745f39dc3", "fetched_at": "2026-08-28T04:07:41.648654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/qwopqwop200/GPTQ-for-LLaMa"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 91, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1276, "days_push": 781, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}