{"adoption": {"forks": 91, "observed_at": "2026-08-28T04:03:23.814513+00:00", "stars": 1053}, "canonical_url": "https://ross.abutalabs.com/products/optimum-quanto", "card": {"archived": false, "artifact_type": "library", "description": "A pytorch quantization backend for optimum", "domain": ["large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "sdk"], "health_score": 91, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["huggingface/optimum-quanto"], "name": "huggingface/optimum-quanto", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-25T17:54:57+00:00", "repo": "huggingface/optimum-quanto", "stars": 1053, "tags": ["pytorch", "quantization", "huggingface", "model-compression", "int8", "int4", "float8", "safetensors", "gpu"], "topics": ["pytorch", "quantization", "optimum"], "urls": [], "use_cases": ["quantize a huggingface llm to int8 or int4", "reduce gpu memory usage of a pytorch model", "quantize pytorch models with float8 weights and activations", "run quantized inference on mps or cuda", "save and reload quantized models with safetensors", "speed up matrix multiplications with int8 int4 kernels"], "what_it_is": "Optimum Quanto is a PyTorch quantization backend for Hugging Face Optimum that quantizes model weights (int2/int4/int8/float8) and activations (int8/float8) with support for CUDA and MPS devices. It provides a seamless workflow from float to dynamic to static quantization, with serialization compatible with PyTorch weight_only and safetensors.", "when_to_avoid": ["you need production-ready quantization with active development - use bitsandbytes or torchAO instead", "you need torch.compile (dynamo) compatibility", "you need optimized kernels for all mixed matrix multiplications on all devices"], "when_to_choose": ["you need versatile eager-mode quantization for non-traceable PyTorch models", "you want to quantize Hugging Face models and serialize them with safetensors", "you need quantization on MPS (Apple Silicon) as well as CUDA"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/optimum-quanto", "repo": "huggingface/optimum-quanto", "role": "main", "score": 70}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:23.814513+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:59:21.386034+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cf9b11b5cefe000709145d32c606c57f48c00581c9e5cab5d62490bd478fece5", "fetched_at": "2026-08-28T04:03:23.814513+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/optimum-quanto"}, {"content_hash": "6ee854039d3379a72dce8924d396fe759f393f61085aa8e75d903117c38a10c4", "fetched_at": "2026-08-29T13:01:00.748299+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/optimum-quanto/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 77, "rhythm": 28}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1079, "days_push": 8, "days_rel": 545, "gap_med": 77.5, "n_releases_24m": 3}, "score": 70, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}