Skip to content

Commit e0a54de

Browse files
authored
chore(model gallery): add smolvlm2-500m-video-instruct (#5416)
Signed-off-by: Ettore Di Giacinto <[email protected]>
1 parent 6bc2ae5 commit e0a54de

File tree

1 file changed

+21
-0
lines changed

1 file changed

+21
-0
lines changed

gallery/index.yaml

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -85,6 +85,27 @@
8585
- filename: mmproj-SmolVLM2-2.2B-Instruct-Q8_0.gguf
8686
sha256: ae07ea1facd07dd3230c4483b63e8cda96c6944ad2481f33d531f79e892dd024
8787
uri: huggingface://ggml-org/SmolVLM2-2.2B-Instruct-GGUF/mmproj-SmolVLM2-2.2B-Instruct-Q8_0.gguf
88+
- !!merge <<: *smolvlm
89+
name: "smolvlm2-500m-video-instruct"
90+
icon: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM2_banner.png
91+
urls:
92+
- https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct
93+
- https://huggingface.co/ggml-org/SmolVLM2-500M-Video-Instruct-GGUF
94+
description: |
95+
SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content.
96+
The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks.
97+
This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited.
98+
overrides:
99+
parameters:
100+
model: SmolVLM2-500M-Video-Instruct-f16.gguf
101+
mmproj: mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf
102+
files:
103+
- filename: SmolVLM2-500M-Video-Instruct-f16.gguf
104+
sha256: 80f7e3f04bc2d3324ac1a9f52f5776fe13a69912adf74f8e7edacf773d140d77
105+
uri: huggingface://ggml-org/SmolVLM2-500M-Video-Instruct-GGUF/SmolVLM2-500M-Video-Instruct-f16.gguf
106+
- filename: mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf
107+
sha256: b5dc8ebe7cbeab66a5369693960a52515d7824f13d4063ceca78431f2a6b59b0
108+
uri: huggingface://ggml-org/SmolVLM2-500M-Video-Instruct-GGUF/mmproj-SmolVLM2-500M-Video-Instruct-f16.gguf
88109
- &qwen3
89110
url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
90111
name: "qwen3-30b-a3b"

0 commit comments

Comments
 (0)