How do I use MTP with gemma4 qat? I'm getting an error

[Milor123]

I am trying to use your compiled version on Windows with CUDA to run

.\llama-server.exe -m "C:\Users\User\.lmstudio\models\mradermacher\gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-GGUF\gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic.Q4_K_S.gguf" --model-draft "C:\Users\User\.lmstudio\models\Janvitos\gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF\gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf" --host 127.0.0.1 --port 10000 -ngl 99 --n-cpu-moe 30 -c 262144 -t 10 -tb 16 -b 2048 -ub 1024 -np 1 -fa on -ctk turbo4 -ctv turbo3 --top-k 20 --repeat-penalty 1.0 --top-p 0.95 --min-p 0.0 --mlock --no-mmap -kvu --spec-type mtp --spec-draft-n-max 2 -fit off

but it doesn't work for me, I get this error.

llama_model_load: error loading model: unknown model architecture: 'gemma4-assistant'
llama_model_load_from_file_impl: failed to load model
srv    load_model: failed to load draft model, 'C:\Users\User\.lmstudio\models\Janvitos\gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF\gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf'
srv operator (): operator (): cleaning up before exit...
main: exiting due to model loading error

I understand that in Qwen the model came with MTP, but in Gemma 4 the QAT model comes alone and with a separate draft. Am I doing something wrong or is this build not yet prepared for this?

What should I do, guys? Thanks!!