What are the hardware requirements for Command A Plus 05 2026 W4a4?

Command A Plus 05 2026 W4a4 requires approximately 132.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Command A Plus 05 2026 W4a4 and how large is it?

Command A Plus 05 2026 W4a4 is developed by CohereLabs, a model with 218.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Command A Plus 05 2026 W4a4?

Command A Plus 05 2026 W4a4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Command A Plus 05 2026 W4a4 by CohereLabs — VRAM 132.9GB

Name: Command A Plus 05 2026 W4a4
Author: CohereLabs

Command A Plus 05 2026 W4a4 is an open-source language model by CohereLabs. Features: 218.8b LLM, VRAM: 132.9GB, License: apache-2.0, LLM Explorer Score: 0.33.

8-bit Ar Base model:coherelabs/command-... Base model:quantized:coherelab... Bg Bn Ca Chat Cohere2 vision Compressed-tensors Conversational Cs Da De Deploy:azure El En Es Et Fa Fi Fil Fr Ga He Hi Hr Hu Id Image-text-to-text Is It Ja Ko Lt Lv Ms Mt Nl No Pa Pl Pt Region:us Ro Ru Safetensors Sharded Sk Sl Sr Sv Ta Te Tensorflow Th Tr Uk Ur Vi Vision Zh

Model Card on HF 🤗: https://huggingface.co/CohereLabs/command-a-plus-05-2026-w4a4

Command A Plus 05 2026 W4a4 Parameters and Internals

LLM Name	Command A Plus 05 2026 W4a4
Repository 🤗	https://huggingface.co/CohereLabs/command-a-plus-05-2026-w4a4
Base Model(s)	CohereLabs/command-a-plus-05-2026 CohereLabs/command-a-plus-05-2026
Model Size	218.8b
Required VRAM	132.9 GB
Updated	2026-08-18
Maintainer	CohereLabs
Model Type	cohere2_vision
Model Files	5.4 GB: 1-of-25 5.4 GB: 2-of-25 5.4 GB: 3-of-25 5.4 GB: 4-of-25 5.4 GB: 5-of-25 5.3 GB: 6-of-25 5.4 GB: 7-of-25 5.4 GB: 8-of-25 5.4 GB: 9-of-25 5.4 GB: 10-of-25 5.4 GB: 11-of-25 5.4 GB: 12-of-25 5.4 GB: 13-of-25 5.4 GB: 14-of-25 5.4 GB: 15-of-25 5.4 GB: 16-of-25 5.4 GB: 17-of-25 5.4 GB: 18-of-25 5.4 GB: 19-of-25 5.4 GB: 20-of-25 5.4 GB: 21-of-25 5.4 GB: 22-of-25 5.4 GB: 23-of-25 5.4 GB: 24-of-25 3.4 GB: 25-of-25
Supported Languages	en ar bg bn ca cs da de el es et fa fi fr ga he hi hr hu id is it ja ko lt lv ms mt nl no pa pl pt ro ru sk sl sr sv ta te th tr uk ur vi zh
Model Architecture	Cohere2VisionForConditionalGeneration
License	apache-2.0
Transformers Version	4.56.2.4
Tokenizer Class	TokenizersBackend
Padding Token	<PAD>

Rank the Command A Plus 05 2026 W4a4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Command A Plus 05 2026 W4a4

Best Alternatives	Context / RAM	Downloads	Likes
Command A Plus 05 2026 Bf16	0K / 437.7 GB	77048	141
Command A Plus 05 2026 Fp8	0K / 219.8 GB	1396	39

Note: green Score (e.g. "73.2") means that the model is better than CohereLabs/command-a-plus-05-2026-w4a4.