Instructions to use staghado/granite-speech-4.0-1b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use staghado/granite-speech-4.0-1b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="staghado/granite-speech-4.0-1b-GGUF",
	filename="granite-speech-4.0-1b-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use staghado/granite-speech-4.0-1b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf staghado/granite-speech-4.0-1b-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf staghado/granite-speech-4.0-1b-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf staghado/granite-speech-4.0-1b-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf staghado/granite-speech-4.0-1b-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 staghado/granite-speech-4.0-1b-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf staghado/granite-speech-4.0-1b-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 staghado/granite-speech-4.0-1b-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf staghado/granite-speech-4.0-1b-GGUF:Q8_0

Use Docker

docker model run hf.co/staghado/granite-speech-4.0-1b-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use staghado/granite-speech-4.0-1b-GGUF with Ollama:
```
ollama run hf.co/staghado/granite-speech-4.0-1b-GGUF:Q8_0
```

Unsloth Studio

How to use staghado/granite-speech-4.0-1b-GGUF 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 staghado/granite-speech-4.0-1b-GGUF 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 staghado/granite-speech-4.0-1b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for staghado/granite-speech-4.0-1b-GGUF to start chatting

Docker Model Runner
How to use staghado/granite-speech-4.0-1b-GGUF with Docker Model Runner:
```
docker model run hf.co/staghado/granite-speech-4.0-1b-GGUF:Q8_0
```

Lemonade

How to use staghado/granite-speech-4.0-1b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull staghado/granite-speech-4.0-1b-GGUF:Q8_0

Run and chat with the model

lemonade run user.granite-speech-4.0-1b-GGUF-Q8_0

List all available models

lemonade list

Granite Speech 4.0 1B — GGUF

GGUF conversion of ibm-granite/granite-4.0-1b-speech for use with llama.cpp audio-multimodal support (see PR #22101).

File	Quant	Size
`granite-speech-4.0-1b-Q8_0.gguf`	Q8_0	~1.8 GB
`mmproj-granite-speech-4.0-1b-f16.gguf`	f16	~1.1 GB

The LLM is quantized to Q8_0; the audio encoder + QFormer projector (mmproj) stays at f16 because llama-quantize does not support the clip architecture used by audio projectors.

Usage

One-shot CLI

llama-mtmd-cli -hf staghado/granite-speech-4.0-1b-GGUF \
  --audio my.wav \
  -p "can you transcribe the speech into a written format?" \
  --jinja --temp 0

Server (OpenAI-compatible)

llama-server -hf staghado/granite-speech-4.0-1b-GGUF --jinja

Then POST to /v1/chat/completions:

{
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "can you transcribe the speech into a written format?"},
      {"type": "input_audio", "input_audio": {"data": "<base64 wav>", "format": "wav"}}
    ]
  }]
}

Audio input requirements: 16 kHz mono WAV (or MP3). From the GGUF's load_hparams: n_mel_bins=160, audio_n_fft=512, audio_window_len=400, audio_hop_len=160, audio_sample_rate=16000.

Conversion provenance

Produced with llama.cpp master (commit 2e97c5f96, build 9100) using:

python convert_hf_to_gguf.py granite-src --outtype f16 --outfile granite-speech-4.0-1b-f16.gguf
python convert_hf_to_gguf.py granite-src --outtype f16 --mmproj --outfile mmproj-granite-speech-4.0-1b-f16.gguf
llama-quantize granite-speech-4.0-1b-f16.gguf granite-speech-4.0-1b-Q8_0.gguf Q8_0

License

Inherits Apache 2.0 from the base model.

Downloads last month: 212

GGUF

Model size

2B params

Architecture

granite

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for staghado/granite-speech-4.0-1b-GGUF

Base model

ibm-granite/granite-4.0-1b-base

Finetuned

ibm-granite/granite-4.0-1b-speech

Quantized

(7)

this model