SmolVLM GGUF - a ggml-org Collection

ggml-org 's Collections

NVIDIA Nemotron 3

Multimodal GGUFs

EmbeddingGemma 300M

InternVL 3 and InternVL 2.5

Qwen 2 VL and Qwen 2.5 VL

llama.cpp presets

GGUF LoRA adapters

Gemma 1.1 GGUFs

SmolVLM GGUF

updated Dec 16, 2025

ggml-org/SmolVLM2-2.2B-Instruct-GGUF

2B • Updated Apr 30, 2025 • 11.7k • 28
ggml-org/SmolVLM2-500M-Video-Instruct-GGUF

0.4B • Updated Apr 30, 2025 • 6.95k • 15
ggml-org/SmolVLM2-256M-Video-Instruct-GGUF

0.2B • Updated Apr 30, 2025 • 572 • 9

Note ^ Version 2 (better quality) For "Video" models, input a sequence of images
ggml-org/SmolVLM-Instruct-GGUF

2B • Updated Apr 30, 2025 • 335 • 8
ggml-org/SmolVLM-500M-Instruct-GGUF

0.4B • Updated Apr 30, 2025 • 59.6k • 47
ggml-org/SmolVLM-256M-Instruct-GGUF

0.2B • Updated Apr 30, 2025 • 16.8k • 13

Note ^ Version 1