Vision2.2B official

smolvlm2-2.2b-instruct

by Hugging Face

Lightweight multimodal model that processes video, image and text inputs to generate text; about 5.2GB of GPU RAM for video inference.

#vision #small

arcflare pull ggml-org/SmolVLM2-2.2B-Instruct-GGUF:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

smolvlm2-2.2b-instruct

Lightweight multimodal model that processes video, image and text inputs to generate text; about 5.2GB of GPU RAM for video inference.

Get it

arcflare pull ggml-org/SmolVLM2-2.2B-Instruct-GGUF:Q4_K_M

arcflare run smolvlm2-2.2b-instruct

ArcFlare reads the GGUF header and loads it at the largest context your free VRAM can actually hold. Use arcflare fit to see that before downloading anything else, or arcflare use opencode to code with it.

Highlights

Downloads the Q4_K_M file by default: 1.1 GB. Also published: Q8_0 (1.9 GB), f16 (3.6 GB)
Reads images: the download also fetches the vision projector (mmproj), about 1 GB more
Trained for a 8K context
Licence: Apache-2.0. Read it before commercial use

Sizes

2.2b · 1.1GB

Other sizes live in sibling repos: swap the size in the repo name when pulling.

[ 03 ] // relatedmore →

moondream

vikhyat

Vision

A tiny, fast vision-language model that runs almost anywhere — captioning and visual Q&A on the edge.

size: 1.8B
vram: ~3 GB
license: Apache-2.0

13% of a 24 GB card

#vision #small #captioning

gemma3

Google

Vision

Gemma 3: 1B to 27B, with image understanding from 4B up, 128K context and 140+ languages.

size: 12B
vram: ~9 GB
license: Gemma

38% of a 24 GB card

#vision #chat #multilingual

mistral-small3.1

Mistral AI

Vision

Mistral Small 3.1 24B: fast general model with image understanding and 128K context, under Apache-2.0.

size: 24B
vram: ~16 GB
license: Apache-2.0

67% of a 24 GB card

#vision #chat #tools