Command R

What Command R is for

Command R is a general-purpose open-weights model from Cohere, released in 2024-03 with a single 35B size and 128K of context, licensed CC-BY-NC (research) / Cohere License (commercial). The catalogue records its strength as RAG with strong tool use.

Sizes and memory

The 35B needs about 22 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
35B	22 GB	33 GB	Apple M4 Max

Hardware that runs Command R

8 of the 19 cards in our hardware guide hold at least one size of Command R at Q4_K_M. The cheapest that does is the Apple M4 Max at about $2400, running the 35B.

The largest size any of them holds is the 35B at 22 GB, on the Apple M4 Max (36 GB at 410 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 3 recorded uses for Command R: RAG, tools, multilingual. It is tagged RAG, tools, multilingual, chat.

Where Command R sits in the Command family

Command R is the only Command entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

It ships under the CC-BY-NC (research) / Cohere License (commercial), which is neither a standard open-source licence nor a closed one. Read the terms before shipping anything commercial on top of it.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

How to run Command R locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for Command R at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "Command R GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.