Adjust docs

This commit is contained in:
Nicolas Mowen 2025-08-15 06:29:43 -06:00
parent 16fb68d859
commit f9c0999ad3

View File

@ -29,12 +29,11 @@ You must use a vision capable model with Frigate. Current model variants can be
The following models are recommended: The following models are recommended:
| Model | Size | Recommended Features | | Model | Size | Notes |
| ----------------- | ------ | -------------------- | | ----------------- | ------ | ----------------------------------------------------------- |
| `minicpm-v:8b` | 5.5 GB | Review Summary | | `gemma3:4b` | 3.3 GB | Strong frame-to-frame understanding, slower inference times |
| `qwen2.5vl:3b` | 3.2 GB | Review Summary | | `qwen2.5vl:3b` | 3.2 GB | Fast but capable model with good vision comprehension |
| `gemma3:4b` | 3.3 GB | All Features | | `llava-phi3:3.8b` | 2.9 GB | Lightweight and fast model with vision comprehension |
| `llava-phi3:3.8b` | 2.9 GB | All Features |
:::note :::note