Jamba 1.5-Large TPS calculator
Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.
Calculated for this model
818 cards we hold specifications for
Smallest card that fits
Radeon Instinct MI325X
256 GB · IQ4_XS · 51.8 tok/s
Fastest card
B300
83.2 tok/s · 288 GB
Which GPUs can run Jamba 1.5-Large?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
4 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
83.2
tok/s
50–133 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 234.4 GB | Q4_K_M | Tight |
|
66.5
tok/s
40–106 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 234.4 GB | Q4_K_M | Tight |
|
66.5
tok/s
40–106 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 234.4 GB | Q4_K_M | Tight |
|
51.8
tok/s
31–83 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 211.3 GB | IQ4_XS | Tight |
Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- AI21 Labs
- Organisation type
- Industry
- Country
- Israel
- Published
- 22 August 2024
- Authors
- Barak Lenz, Alan Arazi, Amir Bergman, Avshalom Manevich, Barak Peleg, Ben Aviram, Chen Almagor, Clara Fridman, Dan Padnos, Daniel Gissin, Daniel Jannai, Dor Muhlgay, Dor Zimberg, Edden M Gerber, Elad Dolev, Eran Krakovsky, Erez Safahi, Erez Schwartz, Gal Cohen, Gal Shachaf, Haim Rozenblum, Hofit Bata, Ido Blass, Inbal Magar, Itay Dalmedigos, Jhonathan Osin, Julie Fadlon, Maria Rozman, Matan Danos,…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation, Chat, Translation, Question answering
- Approach
- Self-supervised learning
- Numerical format
- BF16
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 398B
- Training data
- tokens
94B active/398B total
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H100 SXM5 80GB
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (restricted use)
- Training code
- Unreleased
- Hugging Face
- ai21labs
Commercial use allowed up to $50M USD annual revenue.
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Why it is tracked
- Training cost
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs that run Jamba 1.5-Large
Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.
The smallest GPUs that still run Jamba 1.5-Large
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
What the numbers mean
Hardware requirements in practice
Minimum card
Radeon Instinct MI325X
Memory needed
211.3 GB
Fastest
83.2 tok/s
At 398B parameters, Jamba 1.5-Large is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 4 of the cards we track can hold it on their own, and all of them are datacentre parts.
The entry point is the Radeon Instinct MI325X: 256 GB of memory, IQ4_XS compression, roughly 51.8 tokens per second.
Top of the range is the B300, at roughly 83.2 tokens per second thanks to 8,000 GB/s of bandwidth.
What this model is
Jamba 1.5-Large was published by AI21 Labs, in Israel, in August 2024. It comes out of industry.
It works in Language, and is recorded as doing language modeling/generation, Chat, Translation, Question answering.
Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the ai21labs organisation on Hugging Face.
What decides the speed
Half the cards that hold it manage more than 66.5 tokens per second, and 4 exceed reading speed outright.
Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.
Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.
What went into building it
Its inclusion criterion is training cost.
Step by step
How to choose a GPU for Jamba 1.5-Large
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Check what it needs before anything else
Look at what Jamba 1.5-Large actually needs — around 211.3 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
-
02
Decide how long your conversations run
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Jamba 1.5-Large.
-
03
Set a quality floor
Each card runs the least-compressed copy it can hold — IQ4_XS on the smallest card that fits. Setting a floor drops the cards that only manage Jamba 1.5-Large by squeezing it further than you would want.
-
04
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for Jamba 1.5-Large. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B300 tops it at 83.2 tok/s.
-
05
Read the fit column last
The fit column separates cards that just manage Jamba 1.5-Large from those with room to spare. Buy for the second if the context might grow.
-
06
See what else that card runs
Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Jamba 1.5-Large alone — a card is usually bought for more than one model.
Answers
Jamba 1.5-Large — common questions
What GPU do I need to run Jamba 1.5-Large?
The smallest card in our catalogue that holds Jamba 1.5-Large is the Radeon Instinct MI325X, with 256 GB of memory. It runs the model at IQ4_XS using about 211.3 GB, and produces roughly 51.8 tokens per second. 4 cards in total can run it.
How fast is Jamba 1.5-Large on a GPU?
It depends on the card. The quickest we calculate is a B300 at about 83.2 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 4 of the cards that can run Jamba 1.5-Large clear that.
How much VRAM does Jamba 1.5-Large need?
About 211.3 GB at IQ4_XS compression, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.
Is Jamba 1.5-Large open source?
Its weights are published, so Jamba 1.5-Large can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does Jamba 1.5-Large have?
Jamba 1.5-Large has 398B parameters. 94B active/398B total. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created Jamba 1.5-Large?
Jamba 1.5-Large was published by AI21 Labs, based in Israel, categorised as industry.
When was Jamba 1.5-Large released?
Jamba 1.5-Large was published in August 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Jamba 1.5-Large used for?
Jamba 1.5-Large works in Language, and is recorded as handling language modeling/generation, Chat, Translation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Jamba 1.5-Large?
Its weights are published under the ai21labs organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
Can I run Jamba 1.5-Large if it does not fit in my GPU?
It can be split between the card and system memory, but Jamba 1.5-Large generates painfully slowly that way — the nearest miss we calculate is short by 61.6 GB. Nothing on this page assumes offloading.
Would two GPUs run Jamba 1.5-Large faster?
Two cards buy memory rather than speed. That matters for Jamba 1.5-Large only if one card cannot hold it — 4 can, so a second adds little.
Why does the quantisation differ between cards for Jamba 1.5-Large?
Because capacity varies, so does how hard Jamba 1.5-Large has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these Jamba 1.5-Large speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 50–133 tok/s on the B300, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.