{"adoption": {"forks": 3447, "observed_at": "2026-08-28T04:11:57.671378+00:00", "stars": 32573}, "canonical_url": "https://ross.abutalabs.com/products/airllm", "card": {"archived": false, "artifact_type": "library", "description": "AirLLM 70B inference with single 4GB GPU", "domain": ["large-language-models", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 100, "homepage": null, "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["lyogavin/airllm"], "name": "lyogavin/airllm", "platform": ["python", "windows"], "pushed_at": "2026-08-26T06:20:31+00:00", "repo": "lyogavin/airllm", "stars": 32573, "tags": ["memory-optimization", "model-layer-streaming", "low-vram", "llama", "qwen", "deepseek", "chinese-nlp", "lora", "qlora", "gpu", "linux", "macos"], "topics": ["chinese-nlp", "finetune", "generative-ai", "instruct-gpt", "instruction-set", "llama", "llm", "lora", "open-models", "open-source", "open-source-models", "qlora", "chinese-llm"], "urls": [], "use_cases": ["run a 70B LLM on a 4GB GPU", "run 405B Llama 3.1 on 8GB VRAM", "run DeepSeek-V3 671B on ~12GB of memory", "run large open-source models without quantization", "do LLM inference on consumer GPUs", "run large models on a Mac", "fine-tune with QLoRA on limited VRAM"], "what_it_is": "AirLLM is a Python library that dramatically reduces LLM inference memory usage by streaming model layers (and MoE experts) from disk, enabling 70B models to run on a single 4GB GPU without quantization, distillation, or pruning. It supports models like Llama 3.1 405B, DeepSeek-V3, Qwen, and Kimi K3 on consumer hardware.", "when_to_avoid": ["you need fast, production-grade inference throughput", "you have enough VRAM to fit the model normally", "you need batch serving of many concurrent requests", "you want the lowest latency possible"], "when_to_choose": ["you have limited GPU VRAM but lots of system RAM or disk", "you want to run huge models without quantizing them", "inference speed is not a priority", "you want to experiment with the largest open-source models on consumer hardware"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/airllm", "repo": "lyogavin/airllm", "role": "main", "score": 96}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:57.671378+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:51:56.125915+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a9b1925a0ce5fd6cc44325a506e1a1665df0abb488c917ac3f0b3117a6a33b2f", "fetched_at": "2026-08-28T04:11:57.671378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lyogavin/airllm"}, {"content_hash": "2b504468f9ed08fb3ee5c7ba6b27d3607acd3043e5ab085dddb8d401edd82950", "fetched_at": "2026-08-29T07:48:53.042529+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/airllm/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 84, "rhythm": 98}, "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": 1178, "days_push": 7, "days_rel": 15, "gap_med": 20, "n_releases_24m": 4}, "score": 96, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}