AxForge
Sign in Get started

Model reference · open weights

command-a-vision-07-2025

LLMs CohereLabs Vision + text 1 build Non-commercial 35k dl/mo

command-a-vision-07-2025 is an open-weight language model from Cohere. command-a-vision-07-2025 (FP16) weighs 224 GB; it needs more than the reference configurations below.

  • Cohere Labs Command A Vision is a 112 billion parameter open weights research model designed for enterprise image understanding tasks.
  • It functions as a vision-language model that accepts text and image inputs to generate text, supporting a context length of 32K and six languages including English, French, German, Spanish, Italian, and Portuguese.
  • The model is released under the CC-BY-NC-4.0 license, which restricts use to non-commercial purposes.

Summary of the CohereLabs/command-a-vision-07-2025 model card, 2026-10-01

Hugging Face ↗GitHub ↗

What it is

Released byCohere
Released2025-07-28
Parameters111.9B
VRAM224 GB for the weights

What it runs on

Memory and cards for command-a-vision-07-2025 (FP16)

224 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GB … 8× B200 180 GB
16 smaller cards		does not fit

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms