Skip to content
localmodel.run

Text model · Command R

CR Command R 35B: RAM and VRAM requirements

Command R 35B needs about 22.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~20.05 GB to download; KV cache and overhead add the rest), or about 36.8 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

Command R family · 35B params · released Mar 2024 · 1.4M Ollama pulls.

Shopping for hardware? See what runs Command R 35B →

License CC-BY-NC-4.0 · Non-commercial ↓ 26.8K/mo ♥ 1.1K on HuggingFace
Q4_K_M GGUF
20.05 GB
Q8_0 GGUF
34.63 GB
Memory @ Q4 (4k)
~22.3 GB
Context
128 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Command R 35B runs on 12 of 40 tracked devices at Q4_K_M.

9 run well 3 tight fit 28 too small
Fit check Q4_K_M
No, not enough memory
needs 22.3 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)20.05 GB
+
KV cache (4k)1.4 GB
+
Overhead0.8 GB
=
Total22.3 GB

How context length changes it

4k context ~22.3 GB 32k context ~32.3 GB 128k context ~66.3 GB

Longer context grows the KV cache quickly: Command R 35B needs ~22.3 GB at 4k but ~66.3 GB at 128k, which can push it past a device that fits it at a short context.

Speed drops too: every token re-reads the KV cache, so at 128k context Command R 35B generates at roughly ~31% of its short-context speed. How this is estimated.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 14.7 GB est
Q3_K_M 17.1 GB est
Q4_K_M (default) 20.05 GB
Q5_K_M 24.9 GB est
Q6_K 28.7 GB est
Q8_0 34.63 GB
FP16 70 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run command-r:35b
llama.cpp
$ llama-cli -hf bartowski/c4ai-command-r-v01-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/c4ai-command-r-v01-GGUF

Which devices can run Command R 35B?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Qwen-AgentWorld 35B-A3B 34.7B Next size up Seed-OSS 36B Instruct 36B

Similar models

FAQ

How much VRAM or RAM does Command R 35B need?

At Q4_K_M, Command R 35B needs about 22.3 GB (weights ~20.05 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~36.8 GB.

What is the Q4_K_M GGUF file size of Command R 35B?

The Q4_K_M GGUF file is about 20.05 GB to download, and the Q8_0 GGUF is about 34.63 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~22.3 GB of memory at Q4_K_M.

Can Command R 35B run on a laptop?

Command R 35B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Can I use Command R 35B commercially?

No. CC BY-NC 4.0: non-commercial use only.

Understand the numbers

Short guides to the ideas behind Command R 35B's memory and quant figures.

Cohere Command R 35B, tuned for RAG and tool use, 128K context. Q4_K_M and Q8_0 sizes from the bartowski GGUF repo.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.