deepseek-v4-pro

Updated
25.05.2026
0.4B
Image-Text-to-Text
Llama

A compact 1B vision-language model from OpenBMB that runs image-text-to-text tasks fully on-device, tuned for fast inference on consumer laptops.

More models

NameSize / UsageContextInput
sulphur-2-base
54213 GB421KText

At a glance

  • License: Apache 2.0 — free for commercial use
  • Context length: 128K tokens
  • Languages: 29 languages, English-optimized
  • Minimum hardware: 16 GB RAM, runs on Apple Silicon
  • Strengths: reasoning, coding and multilingual document understanding

Frequently asked questions

No items found.