From 2bc92cce818e7d297527fe04308104f0dfc62181 Mon Sep 17 00:00:00 2001 From: Nicolas Mowen Date: Tue, 23 Sep 2025 07:30:42 -0600 Subject: [PATCH] Update model explanation for genai (#20186) --- docs/docs/configuration/genai/config.md | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/docs/docs/configuration/genai/config.md b/docs/docs/configuration/genai/config.md index bb4d213e1..a49865209 100644 --- a/docs/docs/configuration/genai/config.md +++ b/docs/docs/configuration/genai/config.md @@ -27,13 +27,20 @@ Parallel requests also come with some caveats. You will need to set `OLLAMA_NUM_ You must use a vision capable model with Frigate. Current model variants can be found [in their model library](https://ollama.com/library). Note that Frigate will not automatically download the model you specify in your config, Ollama will try to download the model but it may take longer than the timeout, it is recommended to pull the model beforehand by running `ollama pull your_model` on your Ollama server/Docker container. Note that the model specified in Frigate's config must match the downloaded model tag. +:::tip + +Each model is available in multiple parameter sizes (3b, 4b, 8b, etc.). Larger sizes are more capable of complex tasks and understanding of situations, but requires more memory and computational resources. It is recommended to try multiple models and experiment to see which performs best. + +::: + The following models are recommended: -| Model | Size | Notes | -| ----------------- | ------ | ----------------------------------------------------------- | -| `gemma3:4b` | 3.3 GB | Strong frame-to-frame understanding, slower inference times | -| `qwen2.5vl:3b` | 3.2 GB | Fast but capable model with good vision comprehension | -| `llava-phi3:3.8b` | 2.9 GB | Lightweight and fast model with vision comprehension | +| Model | Notes | +| ----------------- | ----------------------------------------------------------- | +| `Intern3.5VL` | Relatively fast with good vision comprehension +| `gemma3` | Strong frame-to-frame understanding, slower inference times | +| `qwen2.5vl` | Fast but capable model with good vision comprehension | +| `llava-phi3` | Lightweight and fast model with vision comprehension | :::note @@ -124,4 +131,4 @@ genai: provider: azure_openai base_url: https://example-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2023-03-15-preview api_key: "{FRIGATE_OPENAI_API_KEY}" -``` \ No newline at end of file +```