Instructions to use IDEAHQ/ava-storm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use IDEAHQ/ava-storm with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="IDEAHQ/ava-storm", filename="gguf/gemma-4-26B-A4B-it/gemma-4-26B-A4B-it-UD-IQ4_XS.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use IDEAHQ/ava-storm with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf IDEAHQ/ava-storm:Q4_K_M # Run inference directly in the terminal: llama-cli -hf IDEAHQ/ava-storm:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf IDEAHQ/ava-storm:Q4_K_M # Run inference directly in the terminal: llama-cli -hf IDEAHQ/ava-storm:Q4_K_M
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 IDEAHQ/ava-storm:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf IDEAHQ/ava-storm:Q4_K_M
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 IDEAHQ/ava-storm:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf IDEAHQ/ava-storm:Q4_K_M
Use Docker
docker model run hf.co/IDEAHQ/ava-storm:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use IDEAHQ/ava-storm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IDEAHQ/ava-storm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IDEAHQ/ava-storm", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/IDEAHQ/ava-storm:Q4_K_M
- Ollama
How to use IDEAHQ/ava-storm with Ollama:
ollama run hf.co/IDEAHQ/ava-storm:Q4_K_M
- Unsloth Studio new
How to use IDEAHQ/ava-storm 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 IDEAHQ/ava-storm 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 IDEAHQ/ava-storm to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for IDEAHQ/ava-storm to start chatting
- Pi new
How to use IDEAHQ/ava-storm with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf IDEAHQ/ava-storm:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "IDEAHQ/ava-storm:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use IDEAHQ/ava-storm with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf IDEAHQ/ava-storm: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://127.0.0.1:8080/v1 hermes config set model.default IDEAHQ/ava-storm:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use IDEAHQ/ava-storm with Docker Model Runner:
docker model run hf.co/IDEAHQ/ava-storm:Q4_K_M
- Lemonade
How to use IDEAHQ/ava-storm with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull IDEAHQ/ava-storm:Q4_K_M
Run and chat with the model
lemonade run user.ava-storm-Q4_K_M
List all available models
lemonade list
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf IDEAHQ/ava-storm:# Run inference directly in the terminal:
llama-cli -hf IDEAHQ/ava-storm: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 IDEAHQ/ava-storm:# Run inference directly in the terminal:
./llama-cli -hf IDEAHQ/ava-storm: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 IDEAHQ/ava-storm:# Run inference directly in the terminal:
./build/bin/llama-cli -hf IDEAHQ/ava-storm:Use Docker
docker model run hf.co/IDEAHQ/ava-storm:Tali Storm
Tali Storm is the general-purpose on-device LLM (large language model) family for TaliOS.
What it does
Storm is the model that holds a conversation with the user. When you say "draft an email to the team about Friday's release" or "summarize what's on this screen," Storm is what generates the answer. It runs entirely on the device — no audio, screen content, or text leaves the user's hardware to produce a Storm response.
Storm is also the engine behind TaliOS command interpretation: turning a free-form spoken sentence into a structured action that the OS can execute against an app's accessibility surface.
Where it sits in TaliOS
User speech → Tali STT → text → Tali NLU → vector match
│
▼ (no exact hint match)
Tali Storm → action / reply
Storm only runs when faster paths (NLU vector match against the on-screen hint catalogue) cannot resolve the intent. This keeps latency low and battery cost minimal — Storm wakes up for the hard cases, not every utterance.
Variants
Each variant is sized for a specific device class. The TaliOS runtime picks the largest variant that fits the device's RAM and NPU budget at install time.
| Tali ID | Active Params | Architecture | Target |
|---|---|---|---|
| TALI-STORM-2B | 2B | Dense | Phone (low-end) |
| TALI-STORM-4B | 4B | Dense | Phone (mid-range) |
| TALI-STORM-26B-A4B | 4B active | Mixture-of-Experts | Phone (flagship) / HMT-1 |
| TALI-STORM-31B | 31B | Dense | Desktop |
Mixture-of-Experts (MoE) variants have a much larger total parameter count than active count. Only the "active" parameters are loaded for any given token, so memory cost on device is proportional to active params, not total.
Quantization: Q4_K_M for on-device targets (4-bit weights, ~75% size reduction vs full precision). Full-precision weights are retained for desktop.
File format
Shipped weights are wrapped in AON — Tali's encrypted, signed asset container. The .aon extension is the only format the OS or external tooling sees. AON files are decrypted in-process by the TaliOS runtime; they cannot be loaded by third-party inference engines.
License
Proprietary — Intelligent Devices LLC.
- Downloads last month
- 97
4-bit
5-bit
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf IDEAHQ/ava-storm:# Run inference directly in the terminal: llama-cli -hf IDEAHQ/ava-storm: