Instructions to use Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16 # Run inference directly in the terminal: ./llama-cli -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
Use Docker
docker model run hf.co/Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
- LM Studio
- Jan
- Ollama
How to use Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF with Ollama:
ollama run hf.co/Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
- Unsloth Desktop
- Docker Model Runner
How to use Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF with Docker Model Runner:
docker model run hf.co/Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
- Lemonade
How to use Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Radamanthys11/Gemma-4-26B-A4B-it-assistant-GGUF:F16
Run and chat with the model
lemonade run user.Gemma-4-26B-A4B-it-assistant-GGUF-F16
List all available models
lemonade list
- Atomic Chat
--spec-type mtp?
Which version of ik-llama.cpp are you using? If I run it according to the example command, it says that --spec-type mtp is not available. Naturally, if I run it with regular -md, I get the error 'unknown model architecture : 'gemma4_mtp''.

https://github.com/ikawrakow/ik_llama.cpp/blob/main/docs/parameters.md there is no --spec-type mtp here.
Same errors here. I've built the ik-llama.cpp from today's git clone.
llama-server.exe --version
version: 4468 (9a26522a)
built with cc (GCC) 16.1.0 for x86_64-w64-mingw32
Sorry for not making it clear, these versions currently only work on the open PR 1744, so you'll need to build on top of them first.