Model catalog

import ProductFactTable from ‘../../../components/ProductFactTable.astro’;

Whisper transcription models

<ProductFactTable caption=“Whisper catalog” factIds={[‘model_whisper_tiny’, ‘model_whisper_base’, ‘model_whisper_small’, ‘model_whisper_medium’, ‘model_whisper_large_v3_turbo’, ‘model_whisper_large_v3’]} />

Local Ollama and embedding models

<ProductFactTable caption=“Local and provider-aware model catalog” factIds={[‘model_ollama_llama_3_2_3b’, ‘model_ollama_llama_3_1_8b’, ‘model_ollama_llama_3_1_70b’, ‘model_ollama_mistral_7b’, ‘model_ollama_mistral_nemo_12b’, ‘model_ollama_gemma_2_9b’, ‘model_ollama_phi_3_5_3_8b’, ‘model_ollama_qwen_2_5_7b’, ‘model_embedding_nomic’, ‘model_embedding_openai_compatible’]} />

Sizes in the product facts are catalog estimates, not a disk-space, network, performance, or quality guarantee. A remote endpoint must support the fixed embedding model identifier used by remote embedding paths.