Command R Family — local AI model by Cohere

Written by Jakub Rusinowski · Last updated

Newer alternative. Cohere has not released a newer model in this library. If you are choosing today, Mistral Small 4 is a comparable current option. View Mistral Small 4 →

Optimized specifically for RAG (Retrieval Augmented Generation) and tool use. Command R models excel at citing sources and reasoning over provided documents.

Cohere Blog Hugging Face

Variants

The smallest Command R Family variant needs about 22 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
Command R (35B) →
35B
~21.9 GB
Command R+ (104B) →
104B
~63.6 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run Command R Family locally

Install Ollama, then pull the tag.

ollama run command-r

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

CC-BY-NC-4.0Research / non-commercial only

Research / non-commercial only — this licence does NOT permit shipping a commercial product.

Applies to: Command R (35B), Command R+ (104B)

Recommended GPU

The cheapest catalogued GPU that runs Command R Family locally (min 22 GB VRAM) is the NVIDIA GeForce RTX 5090 (32 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
NVIDIA GeForce RTX 5090 32GB
32 GB VRAM · 575 W board power
2026 prices are volatile — check the current listing.

Can I run Command R Family on my GPU?

Command R Family — frequently asked questions

How much VRAM does Command R Family need?

Command R Family needs about 22 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Command R (35B) (22 GB, Q4_K_M); Command R+ (104B) (64 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Command R Family on an RTX 4090 (24 GB)?

Yes — Command R Family runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Command R Family?

Q4_K_M is the best balance of quality and VRAM for Command R Family in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Command R Family with Ollama?

Install Ollama, then run: ollama run command-r. This downloads Command R Family and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.