Cohere/Mixture of Experts

Command A+

Name: Command A+
Author: Cohere

Command A+ is an open source model with 25 billion active parameters and 218B total parameters model optimized for agentic, multilingual, and reasoning-heavy tasks with a focus on enterprise performance, while also providing support for vision inp...

chatcodingreasoningmultilingualagentictool_use

218B

Parameters (25B active)

195K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2026-05-15

Layers

KV Heads

Head Dim

128

Family

command

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	65.3 GB	low
IQ2_M	2.93	80.3 GB	low
Q2_K	3.16	86.6 GB	low
IQ3_XXS	3.25	89.1 GB	low
IQ3_XS	3.5	95.9 GB	low
Q3_K_S	3.64	99.7 GB	low
IQ3_M	3.76	102.9 GB	low
Q3_K_M	4	109.5 GB	low
Q3_K_L	4.3	117.7 GB	moderate
IQ4_XS	4.46	122.0 GB	moderate
Q4_K_S	4.67	127.7 GB	moderate
Q4_K_M	4.89	133.7 GB	good
Q5_K_S	5.57	152.3 GB	good
Q5_K_M	5.7	155.8 GB	good
Q6_K	6.56	179.2 GB	excellent
Q8_0	8.5	232.1 GB	lossless
FP16	16	436.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN COMMAND A+ NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (13)

τ²-Bench80.7

GPQA Diamond76.1

IFBench73.9

MMLU-PRO71.2

AA Long Context46.0

SciCode37.8

AA Intelligence37.2

AA Coding29.3

LiveCodeBench28.7

Terminal-Bench25.0

AIME13.0

MATH-50013.0

HLE11.4

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run command:218b-q4_K_M

Tag may need adjustment — check ollama.com/library/command for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware