{"adoption": {"forks": 226, "observed_at": "2026-08-28T04:06:37.856694+00:00", "stars": 2332}, "canonical_url": "https://ross.abutalabs.com/products/mixtral-offloading", "card": {"archived": false, "artifact_type": "library", "description": "Run Mixtral-8x7B models in Colab or consumer desktops", "domain": ["large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "experimental", "member_repos": ["dvmazur/mixtral-offloading"], "name": "dvmazur/mixtral-offloading", "platform": ["python", "cloud"], "pushed_at": "2024-04-08T08:40:22+00:00", "repo": "dvmazur/mixtral-offloading", "stars": 2332, "tags": ["mixture-of-experts", "quantization", "hqq", "offloading", "mixtral", "colab", "pytorch", "gpu"], "topics": ["colab-notebook", "deep-learning", "google-colab", "language-model", "llm", "mixture-of-experts", "offloading", "pytorch", "quantization"], "urls": [], "use_cases": ["run mixtral 8x7b on google colab", "run mixtral on a consumer gpu with limited vram", "quantize mixture-of-experts model for inference", "offload llm experts between cpu and gpu", "demo notebook for mixtral inference"], "what_it_is": "A Python library enabling efficient inference of Mixtral-8x7B mixture-of-experts language models on limited hardware like Google Colab or consumer desktops. It combines mixed HQQ quantization with per-expert GPU offloading and LRU caching to fit the model into combined GPU and CPU memory.", "when_to_avoid": ["you need a stable CLI or production inference server", "you need speculative expert prefetching or other techniques not yet implemented", "you need support for quantization methods beyond HQQ"], "when_to_choose": ["you want to run Mixtral-8x7B on hardware with limited GPU memory", "you want a Colab-ready demo of quantized MoE inference", "you need HQQ-based mixed quantization with expert offloading"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mixtral-offloading", "repo": "dvmazur/mixtral-offloading", "role": "main", "score": 26}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.856694+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:37:56.730554+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fc047d9cfa027330ea6f4e037e57b47589cb08ed22421503021aa5658eb6059b", "fetched_at": "2026-08-28T04:06:37.856694+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dvmazur/mixtral-offloading"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 70, "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": 992, "days_push": 877, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 26, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}