Feature Extraction
GGUF
llama.cpp
embeddings
multimodal
vision
audio
image-feature-extraction
audio-feature-extraction
Instructions to use MirrorNeuronLab/embeddinggemma-2-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 MirrorNeuronLab/embeddinggemma-2-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible embeddings server: ./build/bin/llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
- Llama new
- LM Studio
- Jan
- Ollama
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Ollama:
ollama run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Docker Model Runner:
docker model run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Lemonade
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.embeddinggemma-2-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download TIMINGS.json from MirrorNeuronLab/embeddinggemma-2-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 10.3 kB
-
https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/TIMINGS.json
- Command line
-
hf download hf://MirrorNeuronLab/embeddinggemma-2-GGUF/TIMINGS.json
-
curl -L -o TIMINGS.json https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/TIMINGS.json
10.3 kB
| [ | |
| { | |
| "stage": "download", | |
| "command": [ | |
| "python3", | |
| "scripts/download_source.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:55:21.409343+00:00", | |
| "finished_utc": "2026-11-01T14:55:53.401870+00:00", | |
| "elapsed_seconds": 31.99252673998126, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "build-configure", | |
| "command": [ | |
| "cmake", | |
| "-S", | |
| "llama.cpp", | |
| "-B", | |
| "llama.cpp/build", | |
| "-DCMAKE_BUILD_TYPE=Release", | |
| "-DGGML_CUDA=OFF", | |
| "-DGGML_NATIVE=ON", | |
| "-DLLAMA_BUILD_TESTS=OFF", | |
| "-DLLAMA_CURL=OFF" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:55:46.632685+00:00", | |
| "finished_utc": "2026-11-01T14:55:48.362987+00:00", | |
| "elapsed_seconds": 1.73029996099649, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "build", | |
| "command": [ | |
| "cmake", | |
| "--build", | |
| "llama.cpp/build", | |
| "--config", | |
| "Release", | |
| "-j", | |
| "16", | |
| "--target", | |
| "llama-quantize", | |
| "llama-server" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:55:48.380276+00:00", | |
| "finished_utc": "2026-11-01T14:56:48.044752+00:00", | |
| "elapsed_seconds": 59.66447541900561, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "dependencies", | |
| "command": [ | |
| ".venv/bin/python", | |
| "-m", | |
| "pip", | |
| "install", | |
| "-r", | |
| "llama.cpp/requirements/requirements-convert_hf_to_gguf.txt", | |
| "huggingface_hub>=0.34.0,<1.0" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:55:49.275061+00:00", | |
| "finished_utc": "2026-11-01T14:56:14.893959+00:00", | |
| "elapsed_seconds": 25.618897876003757, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "dmr-image-pull", | |
| "command": [ | |
| "docker", | |
| "pull", | |
| "docker/model-runner@sha256:9967b6c1092ff01e7cf68119ab25067a1f58e3d1b06873bc16fe1e758bcd914f" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:56:23.532588+00:00", | |
| "finished_utc": "2026-11-01T14:56:27.210774+00:00", | |
| "elapsed_seconds": 3.6781821949989535, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "convert-bf16", | |
| "command": [ | |
| ".venv/bin/python", | |
| "llama.cpp/convert_hf_to_gguf.py", | |
| "source", | |
| "--outtype", | |
| "bf16", | |
| "--model-name", | |
| "embeddinggemma-2", | |
| "--outfile", | |
| "work/embeddinggemma-2-BF16.gguf" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:56:49.790088+00:00", | |
| "finished_utc": "2026-11-01T14:56:53.358771+00:00", | |
| "elapsed_seconds": 3.5686840260168537, | |
| "returncode": 1 | |
| }, | |
| { | |
| "stage": "convert-mmproj", | |
| "command": [ | |
| ".venv/bin/python", | |
| "llama.cpp/convert_hf_to_gguf.py", | |
| "source", | |
| "--mmproj", | |
| "--outtype", | |
| "q8_0", | |
| "--model-name", | |
| "embeddinggemma-2", | |
| "--outfile", | |
| "release/mmproj-embeddinggemma-2-Q8_0.gguf" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:56:50.417675+00:00", | |
| "finished_utc": "2026-11-01T14:56:53.964458+00:00", | |
| "elapsed_seconds": 3.54678301900276, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "cuda-configure", | |
| "command": [ | |
| "cmake", | |
| "-S", | |
| "llama.cpp", | |
| "-B", | |
| "llama.cpp/build-cuda", | |
| "-DCMAKE_BUILD_TYPE=Release", | |
| "-DGGML_CUDA=ON", | |
| "-DCMAKE_CUDA_ARCHITECTURES=121", | |
| "-DGGML_NATIVE=ON", | |
| "-DLLAMA_BUILD_TESTS=OFF", | |
| "-DLLAMA_CURL=OFF" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:57:33.645338+00:00", | |
| "finished_utc": "2026-11-01T14:57:36.272337+00:00", | |
| "elapsed_seconds": 2.626998322986765, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "cuda-build", | |
| "command": [ | |
| "cmake", | |
| "--build", | |
| "llama.cpp/build-cuda", | |
| "--config", | |
| "Release", | |
| "-j", | |
| "8", | |
| "--target", | |
| "llama-server" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:57:36.303210+00:00", | |
| "finished_utc": "2026-11-01T15:01:19.019507+00:00", | |
| "elapsed_seconds": 222.71629584900802, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "convert-bf16-compatible", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/convert_compatible.py", | |
| "source", | |
| "--outtype", | |
| "bf16", | |
| "--model-name", | |
| "embeddinggemma-2", | |
| "--outfile", | |
| "work/embeddinggemma-2-BF16.gguf" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:58:26.671428+00:00", | |
| "finished_utc": "2026-11-01T14:58:39.271335+00:00", | |
| "elapsed_seconds": 12.599901882989798, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "quantize", | |
| "command": [ | |
| "llama.cpp/build/bin/llama-quantize", | |
| "work/embeddinggemma-2-BF16.gguf", | |
| "release/embeddinggemma-2-Q4_K_M.gguf", | |
| "Q4_K_M" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:59:03.341119+00:00", | |
| "finished_utc": "2026-11-01T14:59:05.780096+00:00", | |
| "elapsed_seconds": 2.438970130024245, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "audit", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/audit_gguf.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T14:59:48.642886+00:00", | |
| "finished_utc": "2026-11-01T15:00:09.839507+00:00", | |
| "elapsed_seconds": 21.196617795998463, | |
| "returncode": 1 | |
| }, | |
| { | |
| "stage": "audit-final", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/audit_gguf.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:00:53.569576+00:00", | |
| "finished_utc": "2026-11-01T15:01:15.285176+00:00", | |
| "elapsed_seconds": 21.71559885001625, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "validate-bf16", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/validate_bf16.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:01:15.314013+00:00", | |
| "finished_utc": "2026-11-01T15:01:17.519620+00:00", | |
| "elapsed_seconds": 2.2056051869876683, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "dmr-start", | |
| "command": [ | |
| "bash", | |
| "scripts/start_validation_runner.sh" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:02:00.812758+00:00", | |
| "finished_utc": "2026-11-01T15:02:01.138690+00:00", | |
| "elapsed_seconds": 0.32593187599559315, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "dmr-package", | |
| "command": [ | |
| "env", | |
| "MODEL_RUNNER_HOST=http://127.0.0.1:12435", | |
| "docker", | |
| "model", | |
| "package", | |
| "--gguf", | |
| "$TASK_ROOT/release/embeddinggemma-2-Q4_K_M.gguf", | |
| "--mmproj", | |
| "$TASK_ROOT/release/mmproj-embeddinggemma-2-Q8_0.gguf", | |
| "--license", | |
| "$TASK_ROOT/release/LICENSE", | |
| "--context-size", | |
| "2048", | |
| "mirrorneuronlab/embeddinggemma-2:q4_k_m" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:02:13.051800+00:00", | |
| "finished_utc": "2026-11-01T15:02:15.412325+00:00", | |
| "elapsed_seconds": 2.3605253199930303, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "validate-dmr", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/validate_dmr.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:02:15.594479+00:00", | |
| "finished_utc": "2026-11-01T15:02:17.820825+00:00", | |
| "elapsed_seconds": 2.226341144007165, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "dmr-run", | |
| "command": [ | |
| "env", | |
| "MODEL_RUNNER_HOST=http://127.0.0.1:12435", | |
| "docker", | |
| "model", | |
| "run", | |
| "--detach", | |
| "mirrorneuronlab/embeddinggemma-2:q4_k_m" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:05:52.619080+00:00", | |
| "finished_utc": "2026-11-01T15:05:52.670364+00:00", | |
| "elapsed_seconds": 0.0512839280127082, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "prepare-release", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/prepare_release.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:08:32.554817+00:00", | |
| "finished_utc": "2026-11-01T15:08:34.530224+00:00", | |
| "elapsed_seconds": 1.9754067820031196, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "hf-publish", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/publish_release.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:09:08.040337+00:00", | |
| "finished_utc": "2026-11-01T15:09:09.418174+00:00", | |
| "elapsed_seconds": 1.3778367980266921, | |
| "returncode": 1 | |
| }, | |
| { | |
| "stage": "hf-publish-retry", | |
| "command": [ | |
| "env", | |
| "HF_HOME=$TASK_ROOT/work/hf-home", | |
| "HF_HUB_CACHE=$TASK_ROOT/work/hf-cache", | |
| "HF_XET_CACHE=$TASK_ROOT/work/xet-cache", | |
| "HF_HUB_DISABLE_XET=1", | |
| ".venv/bin/python", | |
| "scripts/publish_release.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:09:46.128486+00:00", | |
| "finished_utc": "2026-11-01T15:10:00.651670+00:00", | |
| "elapsed_seconds": 14.523182463977719, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "hf-verify-public", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/verify_published.py" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:10:32.802376+00:00", | |
| "finished_utc": "2026-11-01T15:10:34.731406+00:00", | |
| "elapsed_seconds": 1.9290308729978278, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "hf-dmr-pull", | |
| "command": [ | |
| "env", | |
| "MODEL_RUNNER_HOST=http://127.0.0.1:12435", | |
| "docker", | |
| "model", | |
| "pull", | |
| "hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:10:33.079233+00:00", | |
| "finished_utc": "2026-11-01T15:10:41.337838+00:00", | |
| "elapsed_seconds": 8.258602988003986, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "hf-dmr-run", | |
| "command": [ | |
| "env", | |
| "MODEL_RUNNER_HOST=http://127.0.0.1:12435", | |
| "docker", | |
| "model", | |
| "run", | |
| "--detach", | |
| "hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:10:41.357601+00:00", | |
| "finished_utc": "2026-11-01T15:10:42.909069+00:00", | |
| "elapsed_seconds": 1.5514679400075693, | |
| "returncode": 0 | |
| }, | |
| { | |
| "stage": "hf-validate-dmr", | |
| "command": [ | |
| ".venv/bin/python", | |
| "scripts/validate_dmr.py", | |
| "--model", | |
| "hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M" | |
| ], | |
| "cwd": "$TASK_ROOT", | |
| "started_utc": "2026-11-01T15:10:42.925462+00:00", | |
| "finished_utc": "2026-11-01T15:10:44.951753+00:00", | |
| "elapsed_seconds": 2.026292441994883, | |
| "returncode": 0 | |
| } | |
| ] | |