OpenModelsHQ

Jamba-v0.1

AI21 LabsLLMMoEApache-2.0

Jamba-v0.1 is an open-weight language model from AI21 Labs with 51.6B parameters (mixture of experts). At 4-bit it needs about 35.2 GB of memory, so the smallest current device that fits it is the L40S.

Overview

Estimated memory at 4-bit
35.2GB

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

Total parameters
51.6B
Mixture of experts, all weights counted
Context window
256K
262,144 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
AI21 Labs
Released
28 Mar 2024
Parameters
51.6B · MoE
Type
Language
Context
262,144 tokens
License
Apache-2.0
HF downloads, 30 days
4,482
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Jamba-v0.1 needs about 35.2 GB at 4-bit, 61.3 GB at 8-bit and 114.6 GB at 16-bit. At 4-bit it fits 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
Q435.2 GB
Q861.3 GB
BF16114.6 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)≈ 35.2 GBTight 98%L40S48 GB memory
8-bit (Q8)≈ 61.3 GBToo big 170%A100 80GB SXM80 GB memory
16-bit (BF16)≈ 114.6 GBToo big 318%H200 SXM141 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

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 Jamba-v0.1 need? At an 8k context, about 35.2 GB at 4-bit, 61.3 GB at 8-bit and 114.6 GB at 16-bit (BF16). A longer context needs more.

Can I run Jamba-v0.1 on a Mac? The smallest current Mac that fits the 4-bit estimate of 35.2 GB is the Mac mini M5 Pro (64GB). We have not found a trusted MLX or GGUF build yet.

Does the full context fit? Jamba-v0.1 supports up to 262,144 tokens of context. 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

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.