GraySoft
Projects Models About FAQ Contact Download guIDE →

ggml-org/smolvlm-256m-instruct-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

ggml-org/smolvlm-256m-instruct-gguf overview

Original model: https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050

ggufbase_model:HuggingFaceTB/SmolVLM-256M-Instructbase_model:quantized:HuggingFaceTB/SmolVLM-256M-Instructlicense:apache-2.0endpoints_compatibleregion:usconversational
ggml-org/smolvlm-256m-instruct-gguf visual
Downloads
33,083
Likes
14
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

4 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
SmolVLM-256M-Instruct-Q8_0.gguf GGUF 166.95 MB Download
SmolVLM-256M-Instruct-f16.gguf GGUF F16 312.62 MB Download
mmproj-SmolVLM-256M-Instruct-Q8_0.gguf GGUF 98.96 MB Download
mmproj-SmolVLM-256M-Instruct-f16.gguf GGUF F16 181.23 MB Download

Model Details Live

Model Slug
ggml-org/smolvlm-256m-instruct-gguf
Author
ggml-org
Pipeline Task
Library
Created
2025-04-21
Last Modified
2025-04-30
Gated
No
Private
No
HF SHA
b9e4379657e1450d04d02eec8e345667265b0a00
License
apache-2.0
Language
Unknown
Base Model
HuggingFaceTB/SmolVLM-256M-Instruct

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "HuggingFaceTB/SmolVLM-256M-Instruct",
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "HuggingFaceTB/SmolVLM-256M-Instruct"
    },
    "hero_image_url": "",
    "summary": "Original model: https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: HuggingFaceTB/SmolVLM-256M-Instruct\n---\n\n# SmolVLM-256M-Instruct\n\nOriginal model: https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct\n\nFor more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:HuggingFaceTB/SmolVLM-256M-Instruct",
    "base_model:quantized:HuggingFaceTB/SmolVLM-256M-Instruct",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 14,
  "downloads": 33083,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-30T11:11:37.000Z",
  "created_at": "2025-04-21T18:59:06.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "6806957aa07d59f3777bc8e6",
  "id": "ggml-org/SmolVLM-256M-Instruct-GGUF",
  "modelId": "ggml-org/SmolVLM-256M-Instruct-GGUF",
  "sha": "b9e4379657e1450d04d02eec8e345667265b0a00",
  "createdAt": "2025-04-21T18:59:06.000Z",
  "lastModified": "2025-04-30T11:11:37.000Z",
  "author": "ggml-org",
  "downloads": 33083,
  "likes": 14,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 6
}