{"adoption": {"forks": 220, "observed_at": "2026-08-28T04:07:30.848930+00:00", "stars": 2936}, "canonical_url": "https://ross.abutalabs.com/products/exllama", "card": {"archived": false, "artifact_type": "library", "description": "A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.", "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": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["turboderp/exllama"], "name": "turboderp/exllama", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2023-09-30T19:06:04+00:00", "repo": "turboderp/exllama", "stars": 2936, "tags": ["gptq", "quantization", "llama", "4-bit", "cuda", "inference-optimization", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["run quantized llama models on a consumer gpu", "load 4-bit gptq models with low vram usage", "fast local inference of llama on rtx 3090 or 4090", "build a local chatbot with a quantized language model", "benchmark inference speed of quantized llama models", "integrate llama inference into a python application"], "what_it_is": "ExLlama is a standalone Python/C++/CUDA implementation of the Llama architecture optimized for running 4-bit GPTQ quantized weights on modern NVIDIA GPUs. It serves as a memory-efficient, fast alternative to the Hugging Face transformers implementation for local LLM inference.", "when_to_avoid": ["you have an older GPU with poor FP16 support (Pascal or earlier) - AutoGPTQ or GPTQ-for-LLaMa are better fits", "you need AMD/ROCm support that is well tested and optimized", "you need a production-hardened, stable solution - the project is still a work in progress"], "when_to_choose": ["you have a modern NVIDIA GPU (RTX 30-series or newer) and want memory-efficient 4-bit GPTQ inference", "you need faster generation than HF transformers with quantized Llama weights", "you want a lightweight standalone library rather than a full inference framework"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/exllama", "repo": "turboderp/exllama", "role": "main", "score": 29}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.848930+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:33:09.896887+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "54a077b845b8e513a2dcf9860a03dd4a60d074cd9d4284a776bd5325fca14a20", "fetched_at": "2026-08-28T04:07:30.848930+00:00", "kind": "readme", "missing": false, "url": "https://github.com/turboderp/exllama"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 86, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1217, "days_push": 1068, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 29, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}