OpenModelsHQ

AI21-Jamba-Large-1.6

AI21 LabsLLMDenseCustom license

AI21-Jamba-Large-1.6 is an open-weight language model from AI21 Labs with 399B parameters. At 4-bit it needs about 284.1 GB of memory, so the smallest device in our directory that fits it is the Mac Studio M3 Ultra (512GB), which is discontinued.

Overview

Estimated memory at 4-bit
284.1GB

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

Total parameters
399B
Dense
Context window
Unknown
Not in the model config
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
AI21 Labs
Released
27 Feb 2025
Parameters
399B
Type
Language
Context
Unknown
HF downloads, 30 days
13
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
AI21-Jamba-Large-1.6 needs about 284.1 GB at 4-bit, 501.9 GB at 8-bit and 947 GB at 16-bit. At 4-bit it fits none of the reference devices. 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
Q4284.1 GB
Q8501.9 GB
BF16947 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)≈ 284.1 GBToo big 789%Mac Studio M3 Ultra (512GB)Discontinued512 GB memory
8-bit (Q8)≈ 501.9 GBToo big 1394%No single device in our directory has enough memory
16-bit (BF16)≈ 947 GBToo big 2631%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

No hosted API found.

More about this model

Frequently asked questions

How much memory does AI21-Jamba-Large-1.6 need? At an 8k context, about 284.1 GB at 4-bit, 501.9 GB at 8-bit and 947 GB at 16-bit (BF16). A longer context needs more.

Can I run AI21-Jamba-Large-1.6 on a Mac? No current Mac fits the 4-bit estimate of 284.1 GB. The smallest Mac in our directory that does is the Mac Studio M3 Ultra (512GB), which is discontinued. We have not found a trusted MLX or GGUF build yet.

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

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

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.