Jamba 1.6 Mini TPS calculator

Open weights AI21 Labs 52B parameters March 2025

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

93 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon PRO V710

28 GB · Q3_K_M · 37.4 tok/s

Fastest card

B200

282 tok/s · 180 GB

Which GPUs can run Jamba 1.6 Mini?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

93 cards match

Calculating

					Needs	Quantisation	Fit
282 tok/s 169–452 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	55.4 GB	Q8_0	Comfortable
282 tok/s 169–452 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	55.4 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	55.4 GB	Q8_0	Comfortable
225 tok/s 135–361 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	55.4 GB	Q8_0	Comfortable
180 tok/s 108–289 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	55.4 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	55.4 GB	Q8_0	Comfortable
173 tok/s 104–276 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	55.4 GB	Q8_0	Comfortable
165 tok/s 99–264 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	55.4 GB	Q8_0	Comfortable
162 tok/s 97–259 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	28.1 GB	IQ4_XS	Tight
162 tok/s 97–259 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	28.1 GB	IQ4_XS	Tight
155 tok/s 93–248 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.1 GB	IQ4_XS	Tight
155 tok/s 93–248 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	28.1 GB	IQ4_XS	Tight
147 tok/s 88–235 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	55.4 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	55.4 GB	Q8_0	Comfortable
147 tok/s 88–235 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	55.4 GB	Q8_0	Comfortable
139 tok/s 83–222 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	55.4 GB	Q8_0	Comfortable
127 tok/s 76–203 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	31.2 GB	Q4_K_M	Tight
127 tok/s 76–203 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	31.2 GB	Q4_K_M	Tight
127 tok/s 76–203 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	31.2 GB	Q4_K_M	Tight
119 tok/s 71–190 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	55.4 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	55.4 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	55.4 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	55.4 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	55.4 GB	Q8_0	Comfortable
118 tok/s 71–189 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	37.2 GB	Q5_K_M	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: 6 March 2025

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Language
Task: Language modeling/generation, Question answering, Code generation, Retrieval-augmented generation, Chat, Quantitative reasoning, Table tasks, Translation

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: 52B
Training data: tokens

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

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident

Sources

Where this record came from and when it was last checked.

Reference: AI21’s Jamba 1.6: The Best Open Model for Private Enterprise Deployment
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Jamba 1.6 Mini

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 1.6 Mini

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

What it takes to run this model

Minimum card

Radeon PRO V710

Memory needed

25.1 GB

Fastest

282 tok/s

Jamba 1.6 Mini reaches a parameter count of 52B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 93.

The smallest card that holds it is Radeon PRO V710, with a memory capacity of 28 GB, running it at a compression of Q3_K_M and producing around 37.4 tokens per second.

Top of the range is B200, generating roughly 282 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Jamba 1.6 Mini was published by AI21 Labs, in the country recorded as Israel, during March 2025. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering, Code generation, Retrieval-augmented generation, Chat, Quantitative reasoning, Table tasks, Translation.

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. On Hugging Face it is published under the organisation ai21labs.

Reading the throughput figures

The median result is around 72.0 tokens per second. Exceeding reading speed outright: 89 of them.

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.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Step by step

How to choose a GPU for Jamba 1.6 Mini

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Start from the memory column

Every card here has been checked against Jamba 1.6 Mini, needing around 25.1 GB at a compression of Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Jamba 1.6 Mini.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Jamba 1.6 Mini. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 282 tok/s.
05

Read the fit column last

A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Jamba 1.6 Mini. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
06

Check the card from the other side

Following a card through to its own page shows every other model it can hold, which is the question that follows once you have settled on Jamba 1.6 Mini.

Answers

Jamba 1.6 Mini — common questions

Jamba 1.6 Mini— how much VRAM does it need?

It needs about 25.1 GB at a compression of Q3_K_M, 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.

Jamba 1.6 Mini— is it open source?

Its weights are published, so it 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.

Jamba 1.6 Mini— how many parameters does it have?

It has a parameter count of 52B. 12B active/52B 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.

Jamba 1.6 Mini— who created it?

It was published by AI21 Labs, based in Israel, an organisation categorised as industry.

Jamba 1.6 Mini— when was it released?

It was published in March 2025.

Jamba 1.6 Mini— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Code generation, Retrieval-augmented generation, Chat, Quantitative reasoning, Table tasks, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Jamba 1.6 Mini— where can I download it?

Its weights are published on Hugging Face, under the organisation ai21labs. We do not host model files — this site calculates what hardware is needed to run them.

Jamba 1.6 Mini— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 9.6 GB. Every figure here assumes the whole model is resident on the card.

Jamba 1.6 Mini— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 93. So a second card is rarely the answer here.

Jamba 1.6 Mini— why does the quantisation differ between cards?

Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Jamba 1.6 Mini— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 169–452 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Jamba 1.6 Mini— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon PRO V710, with a memory capacity of 28 GB. It runs the model at a compression of Q3_K_M using about 25.1 GB, and produces roughly 37.4 tokens per second. The number of cards able to run it in total: 93.

Jamba 1.6 Mini— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 282 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 89.

Source

Original publication

Record last updated 28 November 2025

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.

All AI models