Instructions to use infohound/ha-voice-granite-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use infohound/ha-voice-granite-3b-GGUF 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 infohound/ha-voice-granite-3b-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf infohound/ha-voice-granite-3b-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

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 infohound/ha-voice-granite-3b-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

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 infohound/ha-voice-granite-3b-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

Use Docker

docker model run hf.co/infohound/ha-voice-granite-3b-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use infohound/ha-voice-granite-3b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infohound/ha-voice-granite-3b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infohound/ha-voice-granite-3b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infohound/ha-voice-granite-3b-GGUF:Q8_0

Ollama
How to use infohound/ha-voice-granite-3b-GGUF with Ollama:
```
ollama run hf.co/infohound/ha-voice-granite-3b-GGUF:Q8_0
```
Unsloth Desktop

How to use infohound/ha-voice-granite-3b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "infohound/ha-voice-granite-3b-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use infohound/ha-voice-granite-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/infohound/ha-voice-granite-3b-GGUF:Q8_0
```

Lemonade

How to use infohound/ha-voice-granite-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull infohound/ha-voice-granite-3b-GGUF:Q8_0

Run and chat with the model

lemonade run user.ha-voice-granite-3b-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use infohound/ha-voice-granite-3b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

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 infohound/ha-voice-granite-3b-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use infohound/ha-voice-granite-3b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf infohound/ha-voice-granite-3b-GGUF:Q8_0

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://127.0.0.1:8080/v1 \
  --custom-model-id "infohound/ha-voice-granite-3b-GGUF:Q8_0" \
  --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"

ha-voice-granite-3b-GGUF

A Granite 4.1 3B LoRA fine-tune for Home Assistant voice control — tool calling, state queries, and spoken confirmations — quantized to GGUF for llama.cpp / Ollama.

⚠️ This replaces infohound/ha-voice-7b-GGUF

Please use this model instead. The older 7B model is deprecated and no longer maintained. This one is smaller (3.6 GB vs 4.7 GB), ~30% faster (240 ms vs 341 ms), quantized at higher precision (Q8_0 vs Q4_K_M), and has an 8× larger context window — while fixing two behaviours the old model got wrong.

Why replace the 7B?

The v1 7B model executed tool calls correctly but had two production problems:

It frequently returned no speech after a tool call. Home Assistant then raises Last content in chat log is not an AssistantContent and the user hears "Unable to get response" even though the action succeeded. Deployments worked around it with a synthetic "Done" fallback patch.
It went silent entirely above ~1,200 prompt tokens — no content, no tool call. Real Home Assistant prompts are ~2,900 tokens, squarely in the failing range. This was a capability limit, not a context limit; no num_ctx value fixed it.

This model was trained and validated specifically against both.

Validation

Measured with a schema-driven battery: 28 utterances × 3 repetitions against a 17-tool Home Assistant schema, temperature 0.6, at production prompt size.

Model	Total	State queries	Destructive errors	No speech after tool
this model	81/84 (96%)	15/15	0	0/72
stock `granite-4.1-3b`	70/84 (83%)	13/15	2	1/81

Per category: state queries 15/15 · cameras 12/12 · noise robustness 9/9 · refusals 3/3 · actions 42/45.

"Destructive errors" means a question answered with an action tool — e.g. replying to "which lights are on?" by turning lights on, or to "is the front door locked?" by unlocking it. Stock Granite does the latter 2 times in 3. This model does neither.

Performance

Measured on an RTX 4080 SUPER (16 GB), Ollama, num_ctx 65536:

	this model	v1 7B
Latency (production prompt, 16 tools)	240 ms mean	341 ms
Throughput	109.6 tok/s	—
Context	65,536 (fully GPU-resident)	8,192
VRAM	8.54 GB	5.11 GB
Size on disk	3.6 GB	4.7 GB

128k context spills layers to CPU on a 16 GB card; 64k is the practical ceiling and was verified fully resident.

Files

File	Size	Use
`ha-voice-granite-3b-Q8_0.gguf`	3.37 GB	Recommended. 8.5 BPW, minimal quantization loss
`ha-voice-granite-3b-f16.gguf`	6.34 GB	Full precision, for further quantization

A 3–4B model at Q8_0 costs roughly what a 7B costs at Q4_K_M, at much higher fidelity. Aggressive quants (IQ3/IQ4) were found unusable for this task in earlier work; do not go below Q4_K_S.

Usage — Ollama

num_ctx must be set explicitly in the Modelfile; a missing value silently inherits the server default.

FROM ./ha-voice-granite-3b-Q8_0.gguf
PARAMETER num_ctx 65536
# Use the stock Granite 4.1 chat template so <tool_call> tags are parsed
# into OpenAI-format tool_calls:
#   ollama show granite4.1:3b --modelfile

ollama create ha-voice -f Modelfile

The template matters. Home Assistant's OpenAI-compatible integrations read message.tool_calls; without the Granite template the model's <tool_call> tags arrive as plain text and no tool ever executes.

Usage — llama.cpp

llama-server -m ha-voice-granite-3b-Q8_0.gguf -c 65536 --jinja

Training


Base	`ibm-granite/granite-4.1-3b` (3.40B, Apache-2.0)
Method	LoRA, bf16 base (not QLoRA), r=32, α=64, dropout 0.05
Targets	`q/k/v/o_proj`, `gate/up/down_proj` — 62.3M trainable (1.80%)
Data	9,487 conversations, 12,668 tool calls, 18 distinct tools
Schedule	3 epochs / 1,743 steps, cosine, lr 2e-4, warmup 3%
Masking	Completion-only — loss on assistant turns only
Hardware	NVIDIA DGX Spark (GB10), 24 h 52 m
Final loss	train 0.0338 · eval 0.0253

The dataset lesson worth sharing

An earlier attempt at this model advertised seven tools in thousands of prompts and never demonstrated a single call to any of them. Three epochs taught the model to route around those tools toward whatever was demonstrated. The result: asking "which lights are on in the master bedroom?" made it call HassTurnOn — it turned the lights on — 0/3, where the un-tuned base model answered correctly 3/3.

Fine-tuning destroyed a capability the base model already had.

If you fine-tune for tool calling, audit coverage in both directions: every tool your data calls must exist, and every tool your schema offers must actually be called. A tool that is advertised but never demonstrated is worse than one you never offer.

Intended use

Home Assistant voice assistants via an OpenAI-compatible endpoint (Ollama → LiteLLM → HA). Trained on HA intent schemas — HassTurnOn/Off, HassGetState, HassLightSet, HassClimateSetTemperature, HassMediaPause, HassSetVolume, HassSetPosition, HassCancelAllTimers, list intents, and parameterized camera scripts.

Limitations

Known issue: with large tool schemas (~17+ tools), "add X to the shopping list" can select the list-complete intent instead of list-add. Correct with smaller schemas. A training-data artifact; it is non-destructive and will be fixed in a future revision.
Entity and area names in training were randomized for generalization; behaviour on a specific home depends on what Home Assistant exposes.
English only.
The camera intents are specific to a two-script parameterized setup and will not match other configurations.

License

Apache-2.0, inherited from the Granite 4.1 base model.

Downloads last month: 18

GGUF

Model size

3B params

Architecture

granite

Hardware compatibility

8-bit

16-bit

Model tree for infohound/ha-voice-granite-3b-GGUF

Base model

ibm-granite/granite-4.1-3b

Quantized

(61)

this model

infohound
/

ha-voice-granite-3b-GGUF

ha-voice-granite-3b-GGUF

⚠️ This replaces `infohound/ha-voice-7b-GGUF`

Why replace the 7B?

Validation

Performance

Files

Usage — Ollama

Usage — llama.cpp

Training

The dataset lesson worth sharing

Intended use

Limitations

License

Model tree for infohound/ha-voice-granite-3b-GGUF

ha-voice-granite-3b-GGUF

⚠️ This replaces infohound/ha-voice-7b-GGUF

Why replace the 7B?

Validation

Performance

Files

Usage — Ollama

Usage — llama.cpp

Training

The dataset lesson worth sharing

Intended use

Limitations

License

Model tree for infohound/ha-voice-granite-3b-GGUF

⚠️ This replaces `infohound/ha-voice-7b-GGUF`