{"adoption": {"forks": 400, "observed_at": "2026-08-28T04:09:42.989446+00:00", "stars": 6397}, "canonical_url": "https://ross.abutalabs.com/products/turbo-fieldfare", "card": {"archived": false, "artifact_type": "application", "description": "Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook", "domain": ["large-language-models", "artificial-intelligence", "machine-learning"], "enriched": true, "function": ["llm-inference", "gpu-computing", "cli", "gui"], "health_score": 100, "homepage": null, "language": "Swift", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["drumih/turbo-fieldfare"], "name": "drumih/turbo-fieldfare", "platform": ["cli"], "pushed_at": "2026-08-26T13:31:14+00:00", "repo": "drumih/turbo-fieldfare", "stars": 6397, "tags": ["metal", "apple-silicon", "gemma", "on-device-ai", "mixture-of-experts", "ssd-streaming", "low-memory", "local-llm", "openai-compatible-server", "macos", "swift", "gpu", "desktop"], "topics": ["gemma", "gpgpu", "llm", "local-ai", "macos", "metal", "on-device-ai", "swift", "apple-silicon", "gemma4", "gemma4-26b-a4b", "llm-inference", "on-device-llm"], "urls": [], "use_cases": ["run a 26B LLM locally on an 8 GB MacBook", "on-device chatbot inference without cloud APIs", "serve a local OpenAI-compatible LLM endpoint on macOS", "run Gemma 4 with minimal RAM usage", "experiment with Metal GPU kernels for LLM inference", "private offline text generation on Apple Silicon"], "what_it_is": "TurboFieldfare is a custom Swift + Metal runtime that runs Gemma 4 26B-A4B inference in roughly 2 GB of RAM on Apple Silicon Macs by streaming mixture-of-experts weights from SSD. It ships as a native Mac app, CLI, and local OpenAI-compatible server.", "when_to_avoid": ["you need multi-model or cross-platform support", "you don't have Apple Silicon or macOS 26+", "you need fine-tuning or training, not just inference", "you can't spare ~15 GB of disk for the repacked model"], "when_to_choose": ["you have an M-series Mac with limited RAM and want large local LLM inference", "you want a model-specific optimized runtime rather than llama.cpp or MLX wrappers", "you want a native macOS app plus CLI and local server in one tool"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/turbo-fieldfare", "repo": "drumih/turbo-fieldfare", "role": "main", "score": 80}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:42.989446+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.872614+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ef4224d5d4e75a0f3746fdb3e6c9c68c3afea61f06ee67277d80fcf6f6ebd41", "fetched_at": "2026-08-28T04:09:42.989446+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drumih/turbo-fieldfare"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 3, "rhythm": 99}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 47, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 14}, "score": 80, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}