GraySoft
Projects Models About FAQ Contact Download guIDE →

cstr/granite-speech-3.2-8b-gguf q8_0 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

cstr/granite-speech-3.2-8b-gguf overview

GGUF quantisations of ibm-granite/granite-speech-3.2-8b for CrispASR. | Quant | Description | |---|---| | F16 | Full precision | | Q80 | 8-bit | | Q50 | 5-bit | | Q4_K | 4-bit K-quant (recommended) |

ggufautomatic-speech-recognitioncrispasrenbase_model:ibm-granite/granite-speech-3.2-8bbase_model:quantized:ibm-granite/granite-speech-3.2-8blicense:apache-2.0region:us
cstr/granite-speech-3.2-8b-gguf visual
Downloads
87
Likes
0
Pipeline
automatic-speech-recognition
Library
Visibility
Public
Access
Open

Repository Files & Downloads

3 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
granite-speech-3.2-8b-q4_k.gguf GGUF Q4_K 5.55 GB Download
granite-speech-3.2-8b-q5_0.gguf GGUF 2.79 GB Download
granite-speech-3.2-8b-q8_0.gguf GGUF 4.32 GB Download

Model Details Live

Model Slug
cstr/granite-speech-3.2-8b-gguf
Author
cstr
Pipeline Task
automatic-speech-recognition
Library
Created
2026-04-12
Last Modified
2026-04-12
Gated
No
Private
No
HF SHA
8621b0f7973bcbf3756e9e19a64edc176043dbff
License
apache-2.0
Language
en
Base Model
ibm-granite/granite-speech-3.2-8b

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "ibm-granite/granite-speech-3.2-8b",
    "language": [
      "en"
    ],
    "tags": [
      "automatic-speech-recognition",
      "gguf",
      "crispasr"
    ],
    "pipeline_tag": "automatic-speech-recognition",
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "ibm-granite/granite-speech-3.2-8b",
      "language": [
        "en"
      ],
      "tags": [
        "automatic-speech-recognition",
        "gguf",
        "crispasr"
      ],
      "pipeline_tag": "automatic-speech-recognition"
    },
    "hero_image_url": "",
    "summary": "GGUF quantisations of ibm-granite/granite-speech-3.2-8b for CrispASR. | Quant | Description | |---|---| | F16 | Full precision | | Q8_0 | 8-bit | | Q5_0 | 5-bit | | Q4_K | 4-bit K-quant (recommended) |",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: ibm-granite/granite-speech-3.2-8b\nlanguage:\n  - en\ntags:\n  - automatic-speech-recognition\n  - gguf\n  - crispasr\npipeline_tag: automatic-speech-recognition\n---\n\n# granite-speech-3.2-8b-GGUF\n\nGGUF quantisations of [ibm-granite/granite-speech-3.2-8b](https://huggingface.co/ibm-granite/granite-speech-3.2-8b) for [CrispASR](https://github.com/CrispStrobe/CrispASR).\n\n| Quant | Description |\n|---|---|\n| F16 | Full precision |\n| Q8_0 | 8-bit |\n| Q5_0 | 5-bit |\n| Q4_K | 4-bit K-quant (recommended) |\n\n## Usage\n\n```bash\ncrispasr -m granite-speech-3.2-8b-q4_k.gguf -f audio.wav\n```\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "automatic-speech-recognition",
    "crispasr",
    "en",
    "base_model:ibm-granite/granite-speech-3.2-8b",
    "base_model:quantized:ibm-granite/granite-speech-3.2-8b",
    "license:apache-2.0",
    "region:us"
  ],
  "likes": 0,
  "downloads": 87,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-12T04:40:27.000Z",
  "created_at": "2026-04-12T03:24:38.000Z",
  "pipeline_tag": "automatic-speech-recognition",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "69db10767839670c2c59d284",
  "id": "cstr/granite-speech-3.2-8b-GGUF",
  "modelId": "cstr/granite-speech-3.2-8b-GGUF",
  "sha": "8621b0f7973bcbf3756e9e19a64edc176043dbff",
  "createdAt": "2026-04-12T03:24:38.000Z",
  "lastModified": "2026-04-12T04:40:27.000Z",
  "author": "cstr",
  "downloads": 87,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "automatic-speech-recognition",
  "library_name": "",
  "siblings_count": 5
}