Model reference · open weights

c4ai-command-r

LLMs CohereLabs Text gen 1 build Non-commercial 28k dl/mo

c4ai-command-r is an open-weight language model from Cohere. c4ai-command-r-v01 (FP16) weighs 70.0 GB; the smallest configuration that runs it is H100 80 GB.

  • Cohere Labs Command-R is a 35 billion parameter text-generation model designed for reasoning, summarization, and question answering.
  • It supports a 128K context length and is optimized for grounded generation and single-step tool use across ten languages, including English, French, German, Spanish, Italian, Portuguese, Japanese, Korean, Chinese, and Arabic.
  • The model is released under the cc-by-nc-4.0 license.

Summary of the CohereLabs/c4ai-command-r-v01 model card, 2026-10-01

What it is

Released byCohere
Released2024-03-11
Parameters35.0B
VRAM70.0 GB for the weights

What it runs on

Memory and cards for c4ai-command-r-v01 (FP16)

70.0 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 … L40S 48 GB
6 smaller cards
does not fit
A100 80 GBtight
H100 80 GBtight
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

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