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

`ibm-granite/granite-4.0-1b-speech-GGUF` with BF16 quantization, powered by llama.cpp - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.0-1b-speech-GGUF) - [llama.cpp Documentation…

azureFoundry/HuggingFace/ibm-granite-granite-4.0-1b-speech-gguf@1

ibm-granite/granite-4.0-1b-speech-GGUF with BF16 quantization, powered by llama.cpp

GGUF

GGUF is a binary file format optimized for quick loading and saving of models weights, making it highly efficient for inference purposes. It supports multiple quantization schemes, allowing users to choose the best trade-off between performance and resource usage. llama.cpp has native support for GGUF checkpoints, enabling seamless integration and utilization of models stored in this format.

This model's weights come in GGUF format with Q8_0 quantization.

For more information on GGUF format, you can check the Hugging Face docs and the official GGUF documentation.

Transcriptions API

Send Request

You can use cURL or any REST Client to send a request to the Azure ML endpoint with your Azure ML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json" \
    -d '{"model":"ibm-granite/granite-4.0-1b-speech-GGUF","messages":[{"role":"user","content":"What is Deep Learning?"}]}'

Supported Parameters

The following are the only mandatory parameters to send in the HTTP POST request to v1/audio/transcriptions.

  • model (string): Model ID used to generate the response, in this case since only a single model is deployed within the same endpoint you can either set it to ibm-granite/granite-4.0-1b-speech-GGUF or leave it blank instead.
  • file (file): The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

The rest of the parameters are optional, and since this model is powered by llama.cpp with an OpenAI compatible interface on top for the Transcriptions API for text generation, then the I/O interfaces for both generation and streaming are the same as in OpenAI Transcriptions API.

You can find the whole specification of the allowed parameters in the OpenAI Transcriptions API Specification, or alternatively in the endpoint /openapi.json for the current Azure ML Endpoint.

Specifications & capabilities

Input
audio
Output
text
Published model ID
granite-4.0-1b-speech-GGUF
Capabilities
audioInput

Provider specifications & access

1–1 / 1

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

source model id
HuggingFace/ibm-granite-granite-4.0-1b-speech-gguf@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • audio
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    95 / 100

    source id
    stanfordFMTI
    canonical model id
    azureFoundry/HuggingFace/ibm-granite-granite-4.0-1b-speech-gguf@1
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    IBM
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    95 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–5 / 5

    Hugging Face · ibm-granite/granite-4.0-1b-speech-GGUF ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–2 / 2

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace