Instructions to use google/gemma-4-26B-A4B-it-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-26B-A4B-it-assistant with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-26B-A4B-it-assistant") model = AutoModelForCausalLM.from_pretrained("google/gemma-4-26B-A4B-it-assistant") - Notebooks
- Google Colab
- Kaggle
It's possible to use in lm studio?
#1
by Lollo001lollo - opened
How to use the accelerator MTP whit lm studio?
I guess you need to wait until GGUF version come out, or make it yourself.
I think you also will need to wait for LM Studio backend - llama cpp - to support MTP