framework 13 run gemma3 27B on GPU

sh

#install rocm as found here -> https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/quick-start.html
sudo apt update
sudo apt install "linux-headers-$(uname -r)" "linux-modules-extra-$(uname -r)"
sudo apt install python3-setuptools python3-wheel
sudo usermod -a -G render,video $LOGNAME # Add the current user to the render and video groups
wget https://repo.radeon.com/amdgpu-install/6.3.3/ubuntu/noble/amdgpu-install_6.3.60303-1_all.deb
sudo apt install ./amdgpu-install_6.3.60303-1_all.deb
sudo apt update
sudo apt install amdgpu-dkms rocm

#clone llama.cpp
https://github.com/ggml-org/llama.cpp
cd llama.cpp

#build llama.cpp
HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)"     cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx1103 -DLLAMA_CURL=ON -DGGML_HIP_UMA=ON -DCMAKE_BUILD_TYPE=Release     && cmake --build build --config Release -- -j 16

#run llama.cpp
cd build/bin
wget https://huggingface.co/unsloth/gemma-3-27b-it-GGUF/resolve/main/gemma-3-27b-it-Q6_K.gguf?download=true
HSA_OVERRIDE_GFX_VERSION=11.0.0 ./llama-cli -m gemma-3-27b-it-Q6_K.gguf\?download\=true -ngl 10000

#now sit back and listen to that fan go brrrr

Great guide! My fan only goes a little brrrr ;)