{"omc_version":"0.1","id":"google-gemma-4-12b-it","name":"Gemma 4 12B it","provider":"Google","released":"2026-05-23","licence":{"tag":"Apache License 2.0","state":"parsed","url":"https://llmap.ai/licenses/apache-2-0"},"url":"https://huggingface.co/google/gemma-4-12B-it","description":"Gemma 4 12B it is Google's 12-billion-parameter speech-to-text model with weights you can download under a permissive licence. It covers 140 languages and runs fast on benchmark hardware, though its English accuracy sits near the bottom of the field on every condition we measure.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":1},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":76,"of":76,"score":20.86875,"higher_is_better":false,"variant":null}},"relationships":[],"card_meta":{"created":"2026-09-14T20:17:53.374Z","created_by":"LLMap pipeline","last_updated":"2026-09-29T21:30:14.985Z","x_llmap_prices_checked":null,"x_llmap_prices_oldest":null,"x_llmap_prices_newest":null,"source":"https://llmap.ai/models/google-gemma-4-12b-it","omc_spec":"https://github.com/openmodelcard/spec"}}