arcflare_
Vision8B official

minicpm-v-4.5

by OpenBMB

8B multimodal model on Qwen3-8B and SigLIP2-400M for single-image, multi-image and high-FPS video understanding, OCR and document parsing.

#vision
arcflare pull openbmb/MiniCPM-V-4_5-gguf:Q4_K_M

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1
$ 

[ 02 ] // readme

minicpm-v-4.5

8B multimodal model on Qwen3-8B and SigLIP2-400M for single-image, multi-image and high-FPS video understanding, OCR and document parsing.

Get it

arcflare pull openbmb/MiniCPM-V-4_5-gguf:Q4_K_M
arcflare run minicpm-v-4_5

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: 5 GB. Also published: Q5_K_M (5.8 GB), Q6_K (6.7 GB), Q8_0 (8.7 GB)
  • Reads images: the download also fetches the vision projector (mmproj), about 1 GB more
  • Trained for a 40K context
  • Licence: Apache-2.0. Read it before commercial use

Sizes

  • 8b · 5GB

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

[ 03 ] // relatedmore →

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

llama4-scout

Meta

Vision

Llama 4 Scout: a natively multimodal 109B MoE (17B active, 16 experts) with an extremely long context window.

size
109B-A17B
vram
~64 GB
license
Llama 4 Community

2.7× a 24 GB card

#vision #moe #long-context