CohereCommand R

C4ai Command R Plus 08 2024 — Hardware Requirements & GPU Compatibility

ChatFunctions

C4AI Command R+ 08-2024 is Cohere Labs' 103.8-billion-parameter flagship chat model, an August 2024 refresh of the original Command R+ built for retrieval-augmented generation with citations, single-step tool use (function calling), and multi-step agentic tool use across sequential actions. Like the smaller Command R 08-2024 released alongside it, it is an auto-regressive transformer using grouped-query attention, trained and evaluated across a wide multilingual set including English, French, Spanish, German, Japanese, Korean, Arabic, and Simplified Chinese. Cohere positions it as an open-weights research release with more advanced reasoning, summarization, and question-answering capability than the smaller Command R model. At 103.8 billion parameters, it needs a multi-GPU workstation or server to run, even once quantized. Context length is 128,000 tokens. It is released under a Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license plus Cohere's Acceptable Use Policy, restricting the model to non-commercial use. It was published in August 2024.

103.8B params · denseCC BY-NC 4.0Aug 2024171 downloads305 likes6.2K quant downloads

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

C4ai Command R Plus 08 2024 runs on a 96 GB+ Mac or a workstation GPU

Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 73.8 GB · ~8 tok/s

Macs from 48 GB (IQ2_M · ~11 tok/s)

CC BY-NC 4.0

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run C4ai Command R Plus 08 2024

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama

one command · needs Ollama installed

$ollama run hf.co/bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M

Q4_K_M · needs ~73.8 GB · 16K context

Download: c4ai-command-r-plus-08-2024-Q4_K_M/c4ai-command-r-plus-08-2024-Q4_K_M-00001-of-00002.gguf62.75 GB + 1 partbartowski

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 96 GB GPU

The easiest way to try this model
Running in a few minutes, easy setup
Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does C4ai Command R Plus 08 2024 Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	31.4 GB	42.7 GB	78.7 GB	28.6 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Does not fit: needs 36.7 GB
	34.3 GB	45.5 GB	81.6 GB	31.6 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Does not fit: needs 39.5 GB
	35.7 GB	47 GB	83 GB	33.3 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Does not fit: needs 40.9 GB
	38.5 GB	49.8 GB	85.9 GB	36 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Does not fit: needs 43.8 GB
	44.3 GB	55.5 GB	91.6 GB	40.7 GB	3-bit · i-quant — Importance-weighted 3-bit	Does not fit: needs 49.5 GB
	47.1 GB	58.4 GB	94.4 GB	43.6 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Does not fit: needs 52.4 GB
	48.5 GB	59.8 GB	95.9 GB	39.5 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Does not fit: needs 53.8 GB
	48.5 GB	59.8 GB	95.9 GB	46 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Does not fit: needs 53.8 GB
	50.0 GB	61.2 GB	97.3 GB	45.9 GB	3-bit small — 3-bit small quantization	Does not fit: needs 55.2 GB
	51.4 GB	62.7 GB	98.7 GB	47.7 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Does not fit: needs 56.7 GB
	55.7 GB	66.9 GB	103 GB	51 GB	3-bit medium — 3-bit medium quantization	Does not fit: needs 60.9 GB
	57.1 GB	68.4 GB	104.4 GB	59.2 GB	4-bit · legacy — 4-bit legacy quantization	Does not fit: needs 62.4 GB
	58.5 GB	69.8 GB	105.9 GB	55.4 GB	3-bit large — 3-bit large quantization	Does not fit: needs 63.8 GB
	61.4 GB	72.7 GB	108.7 GB	56.2 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Does not fit: needs 66.6 GB
	64.2 GB	75.5 GB	111.6 GB	59.6 GB	4-bit small — 4-bit small quantization	Does not fit: needs 69.5 GB
	68.5 GB	79.8 GB	115.9 GB	62.8 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Does not fit: needs 73.8 GB
	69.9 GB	81.2 GB	117.3 GB	63.5 GB	4-bit large — 4-bit large quantization	Does not fit: needs 75.2 GB
	71.4 GB	82.6 GB	118.7 GB	71.8 GB	5-bit · legacy — 5-bit legacy quantization	Does not fit: needs 76.6 GB
	78.5 GB	89.8 GB	125.9 GB	71.8 GB	5-bit small — 5-bit small quantization	Does not fit: needs 83.8 GB
	81.4 GB	92.6 GB	128.7 GB	73.6 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Does not fit: needs 86.6 GB
	94.2 GB	105.5 GB	141.6 GB	85.2 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 99.5 GB
	114.2 GB	125.5 GB	161.5 GB	110.3 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 119.5 GB
	228.4 GB	239.7 GB	275.7 GB	~207.6 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 233.6 GB

est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

73.8GBat 16K context

Weights: 67.5 GB
KV cache: 6.0 GB
Overhead: 0.3 GB

Doesn't fit RTX 4090 (reference) · needs 49.8 GB more

Or .

Which Hardware Can Run C4ai Command R Plus 08 2024?

Q4_K_M · 68.5 GB

C4ai Command R Plus 08 2024 (Q4_K_M) requires 68.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 90+ GB is recommended. No consumer GPU has enough memory. 30 devices with unified memory can run C4ai Command R Plus 08 2024, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 96GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 36.7 GB8 GB tier →12 GB tier →16 GB tier →

24 GB · RTX 4090referenceDoesn't fit — smallest quant needs 36.7 GB24 GB tier →

Mac 32 GB · Mac Mini M4Doesn't fit — smallest quant needs 36.7 GBMacs →

Mac 64 GB · Mac Studio M4 MaxIQ3_M · 56.7 GB · ~7 tok/s · 16K56.7~716KMacs →

How good is C4ai Command R Plus 08 2024?

llmrun Score blends public benchmark boards into one number; 100 = the average open model.

Not enough data yet for an llmrun Score.

A Score needs results on enough independent boards. How the Composite Score is built

Benchmarks

LMArena Text
LMArena · Oct 2026Arena
1276.3
#121/188 open
Arena
SimpleBench
Epoch AI · Aug 2024Independent
17.4%
#25/25 open
Independent
MMLU
Epoch AI · Aug 2024Lab-reported
69.4%
#29/85 open
Lab-reported
DTBench
Epoch AI · Aug 2024Lab-reported
54.9%
#57/70 open
Lab-reported
LMCA
Epoch AI · Aug 2024Lab-reported
5.0%
#54/56 open
Lab-reported

All 5 C4ai Command R Plus 08 2024 benchmarks

Alternatives to C4ai Command R Plus 08 2024

Command R family · 5 models →

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Llama 4 Scout 17B 16E InstructMeta	82.1	77 GB	—needs > 24 GB	same size
GLM 4.6VZ.ai	—	66 GB	—needs > 24 GB	same size
Ring Flash 2.0Inclusion AI	—	63.1 GB	—needs > 24 GB	same size
Ling Flash 2.0Inclusion AI	—	63.1 GB	—needs > 24 GB	same size
Qwen1.5 110BAlibaba	—	72.4 GB	—needs > 24 GB	same size
Sarvam 105Bsarvamai	—	238.6 GB	—needs > 24 GB	same size

Specifications

Publisher: Cohere
Family: Command R
Parameters: 103.8B
Release Date: 2024-08-21
License: CC BY-NC 4.0

Resources

Frequently Asked Questions

How much VRAM does C4ai Command R Plus 08 2024 need?

C4ai Command R Plus 08 2024 requires 68.5 GB of VRAM at Q4_K_M, or 228.4 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 103.8B × 4.8 bits ÷ 8 = 62.3 GB

KV Cache + Overhead ≈ 6.2 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

VRAM usage by quantization

Q4_K_M

68.5 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run C4ai Command R Plus 08 2024?

Yes, at IQ2_XXS (31.4 GB) or lower. Higher quantizations like IQ2_XS (34.3 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.

What's the best quantization for C4ai Command R Plus 08 2024?

For C4ai Command R Plus 08 2024, Q4_K_M (68.5 GB) offers the best balance of quality and VRAM usage. Q4_K_L (69.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 31.4 GB.

VRAM requirement by quantization

IQ2_XXS

31.4 GB~53%

Q2_K

48.5 GB~75%

Q4_0

57.1 GB~85%

Q4_K_M ★

68.5 GB~89%

Q5_0

71.4 GB~90%

BF16

228.4 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run C4ai Command R Plus 08 2024 on a Mac?

Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run C4ai Command R Plus 08 2024, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 68.5 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 96GB).

Can I run C4ai Command R Plus 08 2024 locally?

Yes — C4ai Command R Plus 08 2024 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is C4ai Command R Plus 08 2024?

At Q4_K_M, C4ai Command R Plus 08 2024 can reach ~70 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 68.5 × 0.65 = ~76 tok/s

Estimated speed at Q4_K_M (68.5 GB)

NVIDIA B200

~76 tok/s

NVIDIA B300

~76 tok/s

AMD Instinct MI350X

~70 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of C4ai Command R Plus 08 2024?

At Q4_K_M, the download is about 62.29 GB. The full-precision BF16 version is 207.62 GB. The smallest option (IQ2_XXS) is 28.55 GB.

Which GPUs can run C4ai Command R Plus 08 2024?

No single consumer GPU has enough VRAM to run C4ai Command R Plus 08 2024 at Q4_K_M (68.5 GB). Multi-GPU or professional hardware is required.

Which devices can run C4ai Command R Plus 08 2024?

30 devices with unified memory can run C4ai Command R Plus 08 2024 at Q4_K_M (68.5 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run C4ai Command R Plus 08 2024

73.8 GB VRAM at 16K context

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/bartowski/c4ai-command-r-plus-08-2024-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/bartowski/c4ai-command-r-plus-08-2024-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve CohereLabs/c4ai-command-r-plus-08-2024 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~228 GB of GPU memory.

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$bartowski/c4ai-command-r-plus-08-2024-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX PRO 6000 Max-Q (96 GB)CheapestCheapest22 GB free	~17 tok/s	$21.76	Deploy on Vast.aifrom $1.33/hr (opens in new tab)	96 GB · 22 GB free · ~17 tok/s · $21.76 / 1M tokens
RTX PRO 6000 (96 GB)22 GB free	~17 tok/s	$25.09	Deploy on Vast.aifrom $1.54/hr (opens in new tab)	96 GB · 22 GB free · ~17 tok/s · $25.09 / 1M tokens
RTX PRO 6000 Max-Q (96 GB)22 GB free	~17 tok/s	$26.80	Deploy on RunPodfrom $1.64/hr (opens in new tab)	96 GB · 22 GB free · ~17 tok/s · $26.80 / 1M tokens
RTX PRO 6000 (96 GB)22 GB free	~17 tok/s	$27.61	Deploy on RunPodfrom $1.69/hr (opens in new tab)	96 GB · 22 GB free · ~17 tok/s · $27.61 / 1M tokens
RTX PRO 6000 Server (96 GB)22 GB free	~15 tok/s	$31.09	Deploy on RunPodfrom $1.69/hr (opens in new tab)	96 GB · 22 GB free · ~15 tok/s · $31.09 / 1M tokens
RTX PRO 6000 Server (96 GB)22 GB free	~15 tok/s	$31.97	Deploy on Vast.aifrom $1.74/hr (opens in new tab)	96 GB · 22 GB free · ~15 tok/s · $31.97 / 1M tokens
H200 SXM (141 GB)67 GB free	~46 tok/s	$21.92	Deploy on RunPodfrom $3.59/hr (opens in new tab)	141 GB · 67 GB free · ~46 tok/s · $21.92 / 1M tokens
H200 NVL (141 GB)67 GB free	~46 tok/s	$23.02	Deploy on Vast.aifrom $3.77/hr (opens in new tab)	141 GB · 67 GB free · ~46 tok/s · $23.02 / 1M tokens

Compare GPUs →

Your own private copy of C4ai Command R Plus 08 2024 · Q4_K_M · OpenAI-compatible API

The pod’s first start downloads ~62 GB, billed while it loads.

Open the pod on RunPod
Deploy on RunPodRTX PRO 6000 · $2.49/hr (opens in new tab)
New to RunPod? Sign up and add credit first. If that GPU is gone, pick another with at least 96 GB.
2
Set the model and your key
Press Set overrides → Environment variables. The first variable is already there; set its value:
Key
LLAMA_ARG_HF_REPO
Value
bartowski/c4ai-command-r-plus-08-2024-GGUF:Q4_K_M
Press Add Environment variable for your key:
Key
LLAMA_API_KEY
Value
Make up your own key
A long password works. You’ll paste it below as the API key. Without it, anyone who finds the pod’s address can use it.Also set Container disk to 90 GB.Then Set overrides.
Deploy
Press Deploy Pod. Usually ready in 15–60 min.

Use it

RunPod → your pod → Connect → HTTP 8080, copy the link. The key is the one you made up in step 2.

Endpoint URL

API key

Chats and keys stay only in this browser.

https://<POD_ID>-8080.proxy.runpod.net/v1

RunPod → your pod → Connect → HTTP 8080 gives this address. The API key is the one from step 2.

from openai import OpenAI
client = OpenAI(base_url="https://<POD_ID>-8080.proxy.runpod.net/v1", api_key="YOUR_KEY")
r = client.chat.completions.create(
    model="any",
    messages=[{"role": "user", "content": "Hello!"}])
print(r.choices[0].message.content)

Works with any OpenAI client.

https://<POD_ID>-8080.proxy.runpod.net/v1

RunPod → your pod → Connect → HTTP 8080 gives this address. The API key is the one from step 2.

Free on Windows, macOS, Linux, iOS, Android and the web.

Open the web app ↗ (opens in a new tab)Download ↗ (opens in a new tab)

1. Settings → Model Provider → Add → Add Custom Provider
2. API Mode OpenAI API Compatible; paste the API key and the base URL as API Host
3. Model → Fetch, pick the model
4. New chat → pick the provider → start chatting

Free and open source for Windows, macOS and Linux.

Download Jan ↗ (opens in a new tab)

1.Settings → next to Model Providers press +
2.API format OpenAI-compatible; Base URL is the base URL above (with /v1); API key is your key; Create
3.If no model appears, click + in Models and type any
4.New chat → pick the model → start chatting