OpenModelsHQ

c4ai-command-r-v01

Cohere LabsLLMDenseCC BY-NC 4.0

c4ai-command-r-v01 is an open-weight language model from Cohere Labs with 35B parameters. At 4-bit it needs about 24.9 GB of memory, so the smallest current device that fits it is the Radeon AI PRO R9700.

Overview

Estimated memory at 4-bit
24.9GB

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

Total parameters
35B
Dense
Context window
Unknown
Not in the model config
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Cohere Labs
Released
11 Mar 2024
Parameters
35B
Type
Language
Context
Unknown
HF downloads, 30 days
110,090
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
c4ai-command-r-v01 needs about 24.9 GB at 4-bit, 44.1 GB at 8-bit and 83.1 GB at 16-bit. At 4-bit it fits GeForce RTX 5090, DGX Spark, 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
Q424.9 GB
Q844.1 GB
BF1683.1 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)≈ 24.9 GBFits 69%Radeon AI PRO R970032 GB memory
8-bit (Q8)≈ 44.1 GBToo big 123%A100 80GB SXM80 GB memory
16-bit (BF16)≈ 83.1 GBToo big 231%RTX PRO 6000 Blackwell96 GB 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

Start with the MLX files, built for Apple Silicon.

mlx-community/c4ai-command-r-v01-4bitCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

bartowski/c4ai-command-r-v01-GGUFFind compatible hardware

Through an API

No hosted API found.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/c4ai-command-r-v01-4bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf bartowski/c4ai-command-r-v01-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does c4ai-command-r-v01 need? At an 8k context, about 24.9 GB at 4-bit, 44.1 GB at 8-bit and 83.1 GB at 16-bit (BF16). A longer context needs more.

Can I run c4ai-command-r-v01 on a Mac? The smallest current Mac that fits the 4-bit estimate of 24.9 GB is the Mac mini M5 Pro (48GB). An MLX build is available: mlx-community/c4ai-command-r-v01-4bit.

Does the full context fit? We do not have a context length for this model. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

CC BY-NC 4.0. This license allows sharing and adapting with credit, but not for commercial purposes. This summary is not legal advice.

Read CC BY-NC 4.0

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, MLX repository, GGUF repository.