Cohere35B~22 GB VRAM at Q4_K_M

Command R (35B) — VRAM, speed & local setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated March 11, 2024

The RAG specialist. Designed to work with your data. Excellent at following complex instructions and tool use.

Command R (35B) needs about 22 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic89

Creative82

Coding85

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	23 GB	~41 tok/s	Tight
Q3_K_M 3.41 bpw	26.5 GB	~5 tok/s	Offload
Q4_K_M 4.83 bpw	32.7 GB	~4 tok/s	Offload
Q5_K_M 5.67 bpw	36.3 GB	~4 tok/s	Offload
Q6_K 6.56 bpw	40.2 GB	~3 tok/s	Offload
Q8_0 8.50 bpw	48.7 GB	~3 tok/s	Offload
F16 16.00 bpw	81.5 GB	—	Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Command R (35B) VRAM calculator →

Get Command R (35B) running

The cheapest catalogued GPU that runs Command R (35B) is the NVIDIA GeForce RTX 5090 (32 GB).

Buy this hardware NVIDIA GeForce RTX 5090 32GB — 32 GB VRAM · 575 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

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.

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.

Check price on Amazon

How to run Command R (35B)

Install Ollama, then run:

$ollama run command-r

Weights on Hugging Face: CohereForAI/c4ai-command-r-v01 ↗

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters: 35 Billion
Context window: 128,000
Architecture: Dense
Provider: Cohere
Licence: CC-BY-NC
Practical deployment: Single consumer GPU
Specified at: Q4_K_M
System RAM: 32 GB
Record updated: 2024-03-11

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

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

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forragagentwork

Can I run Command R (35B) on my GPU?

Other Command R Family sizes

Command R+ (104B)~64 GB at Q4_K_M

Command R (35B) — frequently asked questions

How much VRAM does Command R (35B) need?

About 22 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Command R (35B) run on an RTX 4090 (24 GB)?

Yes. Command R (35B) needs about 22 GB at Q4_K_M, inside a 24 GB card, at an estimated 4 tokens/sec.

How do I run Command R (35B) locally?

Install Ollama and run `ollama run command-r`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Command R Family come in?

Command R (35B) (22 GB), Command R+ (104B) (64 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.