Tested Gemma-4 E2B-it on Raspberry Pi 4.
the way to convert Gemma-4 E2B-it to gguf
models
https://huggingface.co/baxin/gemma-4-E4B-it-E2B-it-Q4_K_M
llama.cpp
LLM inference in C/C++
Recent API changes
Hot topics
- Hugging Face cache migration: models downloaded with
-hfare now stored in the standard Hugging Face cache directory, enabling sharing with other HF tools. - guide : using the new WebUI of llama.cpp
- guide : running gpt-oss with llama.cpp
- [FEEDBACK] Better packaging for llama.cpp to support downstream consumers 🤗
- Support for the
gpt-ossmodel with native MXFP4 format has been added | PR | Collaboration with NVIDIA | Comment - Multimodal support arrived in
llama-server: #12898 | documentation - VS Code extension for FIM completions: https://github.com/ggml-org/llama.vscode
- Vim/Neovim plugin for FIM completions: https://github.com/ggml-org/llama.vim
- Hugging Face Inference Endpoints now support GGUF out of the box! #9669
- Hugging Face GGUF editor: discussion | tool
- WebGPU support is now available in the browser, see a blog/demo introducing it here.
Quick start
…Step 1 clone the repo
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
Step 2 build
cmake -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release
Step 3 run the model
the command was run from llama.cpp folder and gemma-4-E2B-it-Q4_K_M.gguf is placed in models folder.
folder structure
llama.cpp models
./build/bin/llama-cli -m ../models/gemma-4-E2B-it-Q4_K_M.gguf -t 4 -tb 4 -c 2048 -fa auto --prio 3 -p "hello"
▄▄ ▄▄
██ ██
██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄
██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██
██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀
██ ██
▀▀ ▀▀
build : b9425-0821c5fcf
model : gemma-4-E2B-it-Q4_K_M.gguf
modalities : text
available commands:
/exit or Ctrl+C stop or exit
/regen regenerate the last response
/clear clear the chat history
/read <file> add a text file
/glob <pattern> add text files using globbing pattern
> hello
[Start thinking]
Thinking Process:
1. **Analyze the input:** The input is "hello".
2. **Determine the context/intent:** This is a standard social greeting.
3. **Formulate an appropriate response:** The response should be friendly, polite, and acknowledge the greeting. Standard responses include reciprocating the greeting and offering further interaction (e.g., asking how the user is or offering assistance).
4. **Refine the response:** Keep it open-ended and welcoming.
*Self-Correction/Refinement:* A simple "hello" back is fine, but adding a follow-up makes the interaction more engaging.
5. **Final Output Generation.**
[End thinking]
Hello! How can I help you today?
[ Prompt: 1.3 t/s | Generation: 1.8 t/s ]
Step 4 build with clang
sudo apt install -y clang
rm -rf build
cmake -B build -DCMAKE_BUILD_TYPE=Release \
-DLLAMA_NATIVE=ON \
-DLLAMA_ARM_NEON=ON
cmake --build build --config Release -j
Step 5 run the model
./build/bin/llama-cli -m ../models/gemma-4-E2B-it-Q4_K_M.gguf -t 4 -tb 4 -c 2048 -fa auto --prio 3 -p "hello"
▄▄ ▄▄
██ ██
██ ██ ▀▀█▄ ███▄███▄ ▀▀█▄ ▄████ ████▄ ████▄
██ ██ ▄█▀██ ██ ██ ██ ▄█▀██ ██ ██ ██ ██ ██
██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀
██ ██
▀▀ ▀▀
build : b9425-0821c5fcf
model : gemma-4-E2B-it-Q4_K_M.gguf
modalities : text
available commands:
/exit or Ctrl+C stop or exit
/regen regenerate the last response
/clear clear the chat history
/read <file> add a text file
/glob <pattern> add text files using globbing pattern
> hello
[Start thinking]
Thinking Process:
1. **Analyze the input:** The input is "hello".
2. **Determine the context:** This is a simple, friendly greeting.
3. **Formulate the response goal:** The response should be equally friendly, polite, and open-ended (inviting further conversation).
4. **Draft potential responses:**
* "Hello!" (Too brief, but fine.)
* "Hi there." (Friendly.)
* "Hello! How can I help you today?" (Polite, proactive.)
* "Hello! What can I do for you?" (Direct, service-oriented.)
5. **Select the best response:** A standard friendly greeting followed by an invitation to continue the interaction is usually best.
6. **Final Output Generation.**
[End thinking]
Hello! How can I help you today?
[ Prompt: 2.4 t/s | Generation: 1.5 t/s ]
Result
Prompt ↗️ but Generation ↘️
Unfortunately, it doesn't work for an agent.
Also tried to run LiquidAI/LFM2.5-8B-A1B-GGUF
The result was Prompt: 0.3 t/s | Generation: 0.5t/s ↘️
Conclusion
Raspberry Pi 5 costs around $305, so if you want to run an LLM with fewer than 10B parameters, it seems better to buy a mini PC with 16GB RAM in the $300–400 range.
