Instructions to use ishaanjagyasi/gemma4-e4b-mixer-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 ishaanjagyasi/gemma4-e4b-mixer-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 ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M # Run inference directly in the terminal: llama cli -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M # Run inference directly in the terminal: llama cli -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
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 server with a web UI: ./build/bin/llama serve -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Use Docker
docker model run hf.co/ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with Ollama:
ollama run hf.co/ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
- Unsloth Desktop
- Pi
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with Docker Model Runner:
docker model run hf.co/ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
- Lemonade
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Run and chat with the model
lemonade run user.gemma4-e4b-mixer-assistant-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ishaanjagyasi/gemma4-e4b-mixer-assistant with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "ishaanjagyasi/gemma4-e4b-mixer-assistant:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Gemma 4 E4B Mixer Assistant
This is Gemma 4 E4B (instruct), fine-tuned with LoRA. It turns a producer's or sound engineer's request into tool calls for an Ableton Live-style DAW. For example:
"Bring the kick down a touch, put a reverb on the snare and loop bars 5 to 8." β
set_volume(Kick, -1, relative),add_effect(Snare, Reverb),set_loop(start_bar 5, length 4)
It was made for the University of Michigan course Human-AI Interaction (Fall 2026, Assignment 2). The app, the dataset generator, the evaluation and the training code are on GitHub: ishaanjagyasi/Gemma4-DAW-VUI.
Files
| File | What it is |
|---|---|
gemma4-mixer-Q4_K_M.gguf |
Merged model, 4-bit Q4_K_M (5.3 GB), for Ollama or llama.cpp |
Modelfile |
Ollama Modelfile: Gemma 4 renderer and parser, so tool calls come back as structured tool_calls |
lora/ |
The LoRA adapter (175 MB) for unsloth/gemma-4-E4B-it, for use with PEFT or Unsloth |
Use with Ollama
hf download ishaanjagyasi/gemma4-e4b-mixer-assistant gemma4-mixer-Q4_K_M.gguf Modelfile --local-dir .
ollama create gemma4-mixer -f Modelfile
Then call /api/chat with the app's system prompt, the session as text, the 24 tool schemas, think: false and a
context of at least 8k tokens. The prompt alone is about 3.5k tokens.
Training
- Data: ishaanjagyasi/gemma4-mixer-tool-calls, 3,000 synthetic examples. Each is a session described as text plus a request, with the correct tool calls as the answer. They mix casual, spoken requests ("a touch", "the drums") with precise ones ("-7.5 dB", "126.5 BPM"), with 1β6 requests each.
- Method: LoRA rank 16, alpha 16, on the language model's attention and MLP layers. The loss covers only the assistant's tool calls. Gemma 4's chat template, thinking off.
- Schedule: 1 epoch, 750 steps of batch 4, learning rate 2e-4.
- Hardware: 1 Γ A40 for 6.5 h. Final training loss 0.0067.
Evaluation
Success means the session after the model's tool calls exactly matches the target session.
| Untrained Gemma 4 E4B | This model | |
|---|---|---|
| Held-out validation (100) | β | 98% |
| Study set, standard (200) | 47.0% | 97.0% |
| Study set, hard (84): described tracks, comparisons, unseen slang, same-name tracks, multi-step, long batches | 19.0% | 65.5% |
Limitations. The model was trained on generated requests only. It is weak at:
- values defined relative to another track ("3 dB quieter than the kick");
- telling apart tracks that share a name;
- wording it has not seen.
Check its changes before keeping them.
- Downloads last month
- 37
4-bit