Command R (35B) — VRAM Requirements
Written by Jakub Rusinowski · Last updated March 11, 2024
How much GPU VRAM you need to run Command R Family Command R (35B) by Cohere locally, a 35B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
Command R (35B) needs about 33 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 11.5 GB | 23.0 GB |
| Q3_K_M | 3.41 | 14.9 GB | 26.5 GB |
| Q4_K_M | 4.83 | 21.1 GB | 32.7 GB |
| Q5_K_M | 5.67 | 24.8 GB | 36.3 GB |
| Q6_K | 6.56 | 28.7 GB | 40.2 GB |
| Q8_0 | 8.50 | 37.2 GB | 48.7 GB |
| F16 | 16.00 | 70.0 GB | 81.5 GB |
Switch quantization in the interactive calculator, or see the full Command R Family model page.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/command-r-v1?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=command-r-v1)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.