Command R Models — Hardware Requirements
3 Command R models from Cohere and the community, from the smallest that runs in 15.9 GB of VRAM up to 103.8B parameters. Every row links to full quantization tables and GPU compatibility.
All Command R Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| C4ai Command R7b 12 2024 | 8.0B | 17.7 GB | — | ||
| C4ai Command R V01 | 35.0B | 15.9 GB | — | ||
| C4ai Command R V01 | 35.0B | 16.4 GB | — | ||
| C4ai Command R Plus | 103.8B | 228.4 GB | — |
Frequently Asked Questions
- How much VRAM do I need to run a Command R model?
- The smallest Command R model, C4ai Command R V01, runs from 15.9 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Command R models can I run on a 16 GB GPU?
- 1 of 4 Command R models fit in 16 GB of VRAM at some quantization, including C4ai Command R V01.
- What is the most popular Command R model to run locally?
- C4ai Command R V01 is the most downloaded Command R model in local-friendly quantized formats. It runs from 15.9 GB of VRAM.