OpenModelsHQ

command-a-plus-05-2026-bf16

Cohere LabsVisionMoEApache-2.0

command-a-plus-05-2026-bf16 is an open-weight vision and language model from Cohere Labs with 219B parameters (mixture of experts). At 4-bit it needs about 144.7 GB of memory, so the smallest current device that fits it is the Mac Studio M5 Ultra (256GB).

Overview

Estimated memory at 4-bit
144.7GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
219B
Mixture of experts, all weights counted
Context window
195K
200,000 tokens
Cheapest API, blended / 1M
$0.60
₹57 · Cohere · 3:1 input to output
All Cohere Labs API prices

Key information

Lab
Cohere Labs
Released
11 May 2026
Parameters
219B · MoE
Type
Vision and language
Context
200,000 tokens
License
Apache-2.0
HF downloads, 30 days
15,048
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
command-a-plus-05-2026-bf16 needs about 144.7 GB at 4-bit, 255.4 GB at 8-bit and 481.5 GB at 16-bit. At 4-bit it fits Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q4144.7 GB
Q8255.4 GB
BF16481.5 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 144.7 GBToo big 402%Mac Studio M5 Ultra (256GB)256 GB memory
8-bit (Q8)≈ 255.4 GBToo big 709%RubinAnnounced288 GB memory
16-bit (BF16)≈ 481.5 GBToo big 1338%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

Cohere (fp8) is the cheapest provider we found.

$0.30 / $1.50

Input / output per 1M tokens
₹28 / ₹141 at ₹94.29 per $1

Blended: $0.60 (₹57) per 1M. Ranked by a 3:1 mix of input and output tokens.

Hosted API 1

USD and INR per million tokensAll Cohere Labs API prices
Precision
CohereCheapest$0.60₹57$0.30₹28$1.50₹141192,000FP8
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does command-a-plus-05-2026-bf16 need? At an 8k context, about 144.7 GB at 4-bit, 255.4 GB at 8-bit and 481.5 GB at 16-bit (BF16). A longer context needs more.

Can I run command-a-plus-05-2026-bf16 on a Mac? The smallest current Mac that fits the 4-bit estimate of 144.7 GB is the Mac Studio M5 Ultra (256GB). We have not found a trusted MLX or GGUF build yet.

Does the full context fit? command-a-plus-05-2026-bf16 supports up to 200,000 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is Cohere, at $0.30 per 1M input tokens and $1.50 per 1M output tokens (₹28 and ₹141 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, OpenRouter.