{"adoption": {"forks": 211, "observed_at": "2026-08-28T04:05:08.890766+00:00", "stars": 1593}, "canonical_url": "https://ross.abutalabs.com/products/mllm", "card": {"archived": false, "artifact_type": "library", "description": "Fast Multimodal LLM on Mobile Devices", "domain": ["large-language-models", "artificial-intelligence", "mobile-development", "embedded-systems", "gpu-computing"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning", "sdk", "cli"], "health_score": 96, "homepage": "https://ubiquitouslearning.github.io/mllm/", "language": "C++", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["UbiquitousLearning/mllm"], "name": "UbiquitousLearning/mllm", "platform": ["cross-platform", "cpp", "python", "embedded"], "pushed_at": "2026-08-19T13:16:34+00:00", "repo": "UbiquitousLearning/mllm", "stars": 1593, "tags": ["multimodal-llm", "on-device-inference", "edge-ai", "npu", "qnn", "quantization", "jetson", "ascend", "qwen", "arm-cpu", "android", "ios", "gpu", "mobile"], "topics": ["llama", "multimodal", "ai", "llm", "mobile"], "urls": [], "use_cases": ["run multimodal LLMs on Android phones", "on-device LLM inference on mobile devices", "run Qwen3-VL on Jetson Orin with quantization", "deploy LLM inference on NPU with QNN", "serve quantized LLMs on edge devices", "run vision-language models offline on mobile"], "what_it_is": "MLLM is a fast, lightweight multimodal LLM inference engine written in C++ for mobile and edge devices, with backends for ARM CPU, Qualcomm QNN NPU, OpenCL, CUDA (Jetson), and Ascend NPU. It includes a Python runtime (pymllm) supporting quantized serving of models like Qwen3 and Qwen3-VL.", "when_to_avoid": ["you need a mature general-purpose server LLM stack for datacenter GPUs", "you only need standard CPU inference on desktops where llama.cpp suffices", "you need broad model coverage beyond supported families like Qwen"], "when_to_choose": ["you need fast multimodal LLM inference on mobile or edge hardware", "you target Qualcomm NPU, Ascend, or Jetson devices", "you want C++ on-device inference with quantization support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mllm", "repo": "UbiquitousLearning/mllm", "role": "main", "score": 73}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.890766+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:54:14.617996+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f8fb46726e493e6d731f10df374dc71fc56c16f5a9f7ce75949b3fd35b32c954", "fetched_at": "2026-08-28T04:05:08.890766+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UbiquitousLearning/mllm"}, {"content_hash": "7dbd8f474a8dc9baae37231b9f0ae14b3cead343aaf9fe54b1bb429270f236ee", "fetched_at": "2026-08-29T11:25:02.310669+00:00", "kind": "homepage", "missing": false, "url": "https://ubiquitouslearning.github.io/mllm/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 78, "rhythm": 39}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1099, "days_push": 14, "days_rel": 198, "gap_med": null, "n_releases_24m": 1}, "score": 73, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}