Instructions to use sjakek/gemma4-12b-mtp-assistant 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 sjakek/gemma4-12b-mtp-assistant 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 sjakek/gemma4-12b-mtp-assistant:BF16 # Run inference directly in the terminal: llama cli -hf sjakek/gemma4-12b-mtp-assistant:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf sjakek/gemma4-12b-mtp-assistant:BF16 # Run inference directly in the terminal: llama cli -hf sjakek/gemma4-12b-mtp-assistant:BF16
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 sjakek/gemma4-12b-mtp-assistant:BF16 # Run inference directly in the terminal: ./llama-cli -hf sjakek/gemma4-12b-mtp-assistant:BF16
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 sjakek/gemma4-12b-mtp-assistant:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf sjakek/gemma4-12b-mtp-assistant:BF16
Use Docker
docker model run hf.co/sjakek/gemma4-12b-mtp-assistant:BF16
- LM Studio
- Jan
- vLLM
How to use sjakek/gemma4-12b-mtp-assistant with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sjakek/gemma4-12b-mtp-assistant" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sjakek/gemma4-12b-mtp-assistant", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/sjakek/gemma4-12b-mtp-assistant:BF16
- Ollama
How to use sjakek/gemma4-12b-mtp-assistant with Ollama:
ollama run hf.co/sjakek/gemma4-12b-mtp-assistant:BF16
- Unsloth Studio
How to use sjakek/gemma4-12b-mtp-assistant with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for sjakek/gemma4-12b-mtp-assistant to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for sjakek/gemma4-12b-mtp-assistant to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for sjakek/gemma4-12b-mtp-assistant to start chatting
- Docker Model Runner
How to use sjakek/gemma4-12b-mtp-assistant with Docker Model Runner:
docker model run hf.co/sjakek/gemma4-12b-mtp-assistant:BF16
- Lemonade
How to use sjakek/gemma4-12b-mtp-assistant with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sjakek/gemma4-12b-mtp-assistant:BF16
Run and chat with the model
lemonade run user.gemma4-12b-mtp-assistant-BF16
List all available models
lemonade list
- Atomic Chat
| { | |
| "source_model": "google/gemma-4-12B-it-assistant", | |
| "source_revision": "723932f88886ab714522468b94f9c7ee48d8c9a8", | |
| "requested_repo": "atx/gemma4-12b-mtp-assistant", | |
| "uploaded_repo": "sjakek/gemma4-12b-mtp-assistant", | |
| "requested_repo_status": "blocked: authenticated token has no atx namespace write rights", | |
| "gguf_architecture": "gemma4-assistant", | |
| "llama_cpp_branch": { | |
| "repo": "https://github.com/am17an/llama.cpp", | |
| "branch": "gemma4-mtp", | |
| "commit": "b8e703e", | |
| "local_converter_patch": [ | |
| "Register Gemma4UnifiedAssistantForCausalLM in conversion/__init__.py", | |
| "Register Gemma4UnifiedAssistantForCausalLM on Gemma4AssistantModel in conversion/gemma.py" | |
| ] | |
| }, | |
| "outputs": [ | |
| { | |
| "filename": "gemma-4-12B-it-assistant-BF16.gguf", | |
| "file_type": "MOSTLY_BF16", | |
| "bytes": 861520128, | |
| "sha256": "be2ff6cf6dc9f4d753be846efb990606a5fec1b9c758c7f200112d2431f5e248" | |
| }, | |
| { | |
| "filename": "gemma-4-12B-it-assistant-Q8_0.gguf", | |
| "file_type": "MOSTLY_Q8_0", | |
| "bytes": 465109248, | |
| "sha256": "cb9b46d9ff820b2b9b0d53cc911a2bc27eb2faf84700284047244d8f28883794" | |
| } | |
| ], | |
| "metadata": { | |
| "context_length": 131072, | |
| "assistant_hidden_size": 1024, | |
| "target_hidden_size": 3840, | |
| "num_hidden_layers": 4, | |
| "num_attention_heads": 16, | |
| "head_count_kv": [8, 8, 8, 1], | |
| "shared_kv_layers": 4, | |
| "nextn_predict_layers": 4, | |
| "sliding_window_pattern": [true, true, true, false], | |
| "rope_dimension_count": 512, | |
| "rope_dimension_count_swa": 256, | |
| "required_tensors": [ | |
| "rope_freqs.weight", | |
| "nextn.pre_projection.weight", | |
| "nextn.post_projection.weight" | |
| ] | |
| }, | |
| "runtime_validation": { | |
| "status": "pass", | |
| "target_model": "gemma-4-12b-it-UD-Q6_K_XL.gguf", | |
| "speculative_type": "draft-mtp", | |
| "serving_shape": { | |
| "ctx_size": 131072, | |
| "batch_size": 4096, | |
| "ubatch_size": 512, | |
| "flash_attn": true, | |
| "draft_kv": "q8_0/q8_0" | |
| }, | |
| "checks": [ | |
| { | |
| "name": "gguf_audit", | |
| "result": "pass" | |
| }, | |
| { | |
| "name": "bf16_mtp_generation", | |
| "result": "pass", | |
| "draft_tokens": 6, | |
| "accepted_tokens": 6, | |
| "log": "logs/completion-bf16-mtp.json" | |
| }, | |
| { | |
| "name": "q8_0_mtp_generation", | |
| "result": "pass", | |
| "draft_tokens": 6, | |
| "accepted_tokens": 6, | |
| "log": "logs/completion-q8-mtp.json" | |
| }, | |
| { | |
| "name": "long_context_smoke", | |
| "result": "pass", | |
| "prompt_tokens": 126009, | |
| "predicted_tokens": 8, | |
| "truncated": false, | |
| "log": "logs/completion-q8-mtp-long-context-summary.json" | |
| }, | |
| { | |
| "name": "openai_chat_completion", | |
| "result": "pass", | |
| "log": "logs/openai-chat-final-q8-canonical.json" | |
| } | |
| ] | |
| } | |
| } | |