-
Notifications
You must be signed in to change notification settings - Fork 1.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support for gemma3 from google #12963
Comments
Need to upgrade to Ollama v0.6, this should add support for gemma3 |
@puffer-duck But v0.6 not support intel card accelerate, am i right? |
"error": { |
Yes we need this. Can Intel publish patches to Ollama so that we can compile ourselves? Or setup automatic nightly builds that follow the latest version of Ollama. |
Note this was brought up here: #12950 That is generally about the version disparity versus just |
Please! |
Hi All, Gemma3 is now supported in ipex-llm llamacpp! (Ollama support is in progress—we'll provide updates once it's ready.) Important Notes: The 27B Gemma3 q4_k_m model requires >16GB VMem.
Get Started:Please follow the following steps to try it out: 1. Download the latest ipex-llm llamacpp portable zip:2. Get mmproj.gguf & gemma3 gguf model filesPlease download the pre-quantized version from HF: https://huggingface.co/collections/ggml-org/gemma-3-67d126315ac810df1ad9e913 (You must download both the text model and the mmproj file) Note: Vision capability is available on these model sizes: 3. Run gemma33.1 Linuxngl=99 3.1.1 Text only
3.1.2 Single turn (Vision)
3.2.2 Chat mode (Vision)
3.2 WIN3.2.1 Text only
3.2.2 Single turn (Vision)
3.2.3 Chat mode (Vision)
|
Thank you for your efforts. I see that the portable zip of ollama in the pre-release has been updated to 20250313, but it seems that the ollama portable zip still cannot run gemma3 properly. |
请更新ollama,已支持gemma3
Error: llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade
The text was updated successfully, but these errors were encountered: