diff --git a/opsec/openwebuilocalllms/index.html b/opsec/openwebuilocalllms/index.html index f098a2d..ffe3a4e 100644 --- a/opsec/openwebuilocalllms/index.html +++ b/opsec/openwebuilocalllms/index.html @@ -370,13 +370,48 @@ Go to the Admin settings and proceed with next steps.
To see available models, head to ollama library. Sadly they block Tor traffic so if you have to use Tor, use their chinese mirror.
Next, pick a model you want to download. In our case, we want Gemma 3. Then click on Tags to see all available variants.
+Now, you'll see different sizes and quantization variants the model is available in.
+We want to download 12B variant in Q4_K_M quantization. Comparing the hashes, we see the default gemma3:12b is the same as gemma3:12b-it-q4_K_M. Additionally, you can see that if we put just gemma3, we would get the 4B variant.
+Then, copy the model name we got after clicking on desired variant. If you want to download it via ollama CLI, we also get the full command. In our case Open WebUI needs to know just the model_name:size.
+
+Now, go back to Open WebUI's Admin Settings we opened in the previous section and click on Models tab, then the download icon:
+
+In the Enter model tag field, type gemma3:12b and click the download icon again. It will automatically pull the appropriate model from the ollama library.
+
+After that, just wait for the model download to complete.
+
+Once the progress bar reaches 100%, the model should be added to your library automatically.
+Go to the main page again and check if it's available now.
+