ggml-org/SmolVLM2-256M-Video-Instruct-GGUFSmolVLM2 256M Video Instruct Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2 256M Video Instruct For more info, please refer to this PR: https://github.com/ggml org/llama.cpp/pull/13050

SmolVLM2-256M-Video-Instruct-GGUF

PUBLIC

Mirrored

For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050

License:apache-2.0

imported

huggingface

minio

gguf

base_model:HuggingFaceTB/SmolVLM2-256M-Video-Instruct

base_model:quantized:HuggingFaceTB/SmolVLM2-256M-Video-Instruct

license:apache-2.0

endpoints_compatible

region:us

conversational

1downloads0likesLicense:apache-2.0

Model Card

Edit

SmolVLM2-256M-Video-Instruct

Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct

For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050

Inference Providers

This model isn't deployed by any Inference Provider yet. Deploy this model →

GGUF details

Format

GGUF

Model size

256M params

4 quantization variants

mmproj-SmolVLM2-256M-Video-Instruct-Q8_099 MB

SmolVLM2-256M-Video-Instruct-Q8_0166.9 MB

mmproj-SmolVLM2-256M-Video-Instruct-f16181.2 MB

SmolVLM2-256M-Video-Instruct-f16312.6 MB

Source

Mirrored from an external registry.

Last synced 6/14/2026

Model tree for ggml-org/SmolVLM2-256M-Video-Instruct-GGUF

Base model

HuggingFaceTB/SmolVLM2-256M-Video-Instruct

Files

main

6 files · 759.8 MBHistory

Security scan in progress for 6 files.

main

6 files · 759.8 MB

.gitattributes1.8 KB

mmproj-SmolVLM2-256M-Video-Instruct-f16.ggufLFS181.2 MB

mmproj-SmolVLM2-256M-Video-Instruct-Q8_0.ggufLFS99 MB

README.md289 B

SmolVLM2-256M-Video-Instruct-f16.ggufLFS312.6 MB

SmolVLM2-256M-Video-Instruct-Q8_0.ggufLFS166.9 MB

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy