Kokoro v1.0 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
Tesla C1080
4 GB · Q8_0 · 450 tok/s
Fastest card
B200
41,320 tok/s · 180 GB
Which GPUs can run Kokoro v1.0?
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.
818 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
41,320
tok/s
24,792–66,112 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 0.8 GB | Q8_0 | Comfortable |
|
41,320
tok/s
24,792–66,112 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 0.8 GB | Q8_0 | Comfortable |
|
32,995
tok/s
19,797–52,792 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 0.8 GB | Q8_0 | Comfortable |
|
32,995
tok/s
19,797–52,792 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 0.8 GB | Q8_0 | Comfortable |
|
26,388
tok/s
15,833–42,221 · low confidence |
Radeon Instinct MI300 AMD | 128 GB | 6,550 GB/s | Jan 2023 | 0.8 GB | Q8_0 | Comfortable |
|
25,257
tok/s
15,154–40,411 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 0.8 GB | Q8_0 | Comfortable |
|
25,257
tok/s
15,154–40,411 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 0.8 GB | Q8_0 | Comfortable |
|
24,172
tok/s
14,503–38,675 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 0.8 GB | Q8_0 | Comfortable |
|
21,453
tok/s
12,872–34,324 · low confidence |
Radeon Instinct MI300A AMD | 128 GB | 5,325 GB/s | Dec 2023 | 0.8 GB | Q8_0 | Comfortable |
|
21,453
tok/s
12,872–34,324 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 0.8 GB | Q8_0 | Comfortable |
|
21,453
tok/s
12,872–34,324 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 0.8 GB | Q8_0 | Comfortable |
|
20,350
tok/s
12,210–32,560 · low confidence |
H100 NVL 94 GB NVIDIA | 94 GB | 3,940 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
|
17,354
tok/s
10,413–27,767 · low confidence |
H100 PCIe 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
|
17,354
tok/s
10,413–27,767 · low confidence |
H100 SXM5 80 GB NVIDIA | 80 GB | 3,360 GB/s | Oct 2022 | 0.8 GB | Q8_0 | Comfortable |
|
17,354
tok/s
10,413–27,767 · low confidence |
H100 SXM5 94 GB NVIDIA | 94 GB | 3,360 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
|
17,354
tok/s
10,413–27,767 · low confidence |
H100 SXM5 96 GB NVIDIA | 96 GB | 3,360 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
|
17,354
tok/s
10,413–27,767 · low confidence |
H800 SXM5 NVIDIA | 80 GB | 3,360 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
|
13,214
tok/s
7,928–21,143 · low confidence |
Radeon Instinct MI250 AMD | 128 GB | 3,280 GB/s | Nov 2021 | 0.8 GB | Q8_0 | Comfortable |
|
13,214
tok/s
7,928–21,143 · low confidence |
Radeon Instinct MI250X AMD | 128 GB | 3,280 GB/s | Nov 2021 | 0.8 GB | Q8_0 | Comfortable |
|
11,012
tok/s
6,607–17,619 · low confidence |
Data Center GPU Max 1550 Intel | 128 GB | 3,280 GB/s | Jan 2023 | 0.8 GB | Q8_0 | Comfortable |
|
10,777
tok/s
6,466–17,243 · low confidence |
Data Center GPU Max Subsystem Intel | 128 GB | 3,210 GB/s | Jan 2023 | 0.8 GB | Q8_0 | Comfortable |
|
10,537
tok/s
6,322–16,859 · low confidence |
A100 SXM4 80 GB NVIDIA | 80 GB | 2,040 GB/s | Nov 2020 | 0.8 GB | Q8_0 | Comfortable |
|
10,537
tok/s
6,322–16,859 · low confidence |
A100X NVIDIA | 80 GB | 2,040 GB/s | Jun 2021 | 0.8 GB | Q8_0 | Comfortable |
|
10,537
tok/s
6,322–16,859 · low confidence |
A800 SXM4 80 GB NVIDIA | 80 GB | 2,040 GB/s | Aug 2022 | 0.8 GB | Q8_0 | Comfortable |
|
10,537
tok/s
6,322–16,859 · low confidence |
H100 CNX NVIDIA | 80 GB | 2,040 GB/s | Mar 2023 | 0.8 GB | Q8_0 | Comfortable |
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
- hexgrad
- Published
- 27 January 2025
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Text-to-speech (TTS), Speech synthesis
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
- 82M
- Training data
- tokens
82M
"Few hundred hrs" of training audio data
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.7 × 10²⁰ FLOP
- How it was established
- Hardware
312000000000000 FLOP / GPU / sec * 500 GPU - hours * 3600 sec / hour * 0.3 [assumed utilization] = 1.6848e+20 FLOP
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 A100 SXM4 80 GB
- Chip-hours
- 500
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 (unrestricted)
- Training code
- Unreleased
- Hugging Face
- hexgrad
Apache 2.0 for weights https://huggingface.co/hexgrad/Kokoro-82M Apache 2.0 for inference code https://github.com/hexgrad/kokoro
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
- Kokoro v1.0
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs that run Kokoro v1.0
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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 41,320 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 41,320 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 32,995 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 32,995 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 26,388 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 25,257 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 25,257 tok/s
- 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 24,172 tok/s
- 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 21,453 tok/s
- 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 21,453 tok/s
The smallest GPUs that still run Kokoro v1.0
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 GeForce RTX 4010 4 GB · needs 0.8 GB · Q8_0 · comfortable 496 tok/s
- 02 RTX A400 4 GB · needs 0.8 GB · Q8_0 · comfortable 496 tok/s
- 03 RTX 500 Mobile Ada Generation 4 GB · needs 0.8 GB · Q8_0 · comfortable 661 tok/s
- 04 GeForce RTX 3050 A Mobile 4 GB · needs 0.8 GB · Q8_0 · comfortable 992 tok/s
- 05 Jetson Orin Nano 4 GB 4 GB · needs 0.8 GB · Q8_0 · comfortable 176 tok/s
- 06 Radeon RX 6450M 4 GB · needs 0.8 GB · Q8_0 · comfortable 516 tok/s
- 07 Radeon RX 6550M 4 GB · needs 0.8 GB · Q8_0 · comfortable 580 tok/s
- 08 Radeon RX 6550S 4 GB · needs 0.8 GB · Q8_0 · comfortable 516 tok/s
- 09 Arc A310 4 GB · needs 0.8 GB · Q8_0 · comfortable 416 tok/s
- 10 Arc Pro A30M 4 GB · needs 0.8 GB · Q8_0 · comfortable 430 tok/s
What the numbers mean
Hardware requirements in practice
Minimum card
Tesla C1080
Memory needed
0.8 GB
Fastest
41,320 tok/s
Kokoro v1.0 is small enough at 82M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.
The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 450 tokens per second.
The quickest result comes from a B200 at around 41,320 tokens per second — its 8,000 GB/s of bandwidth is what buys that.
Where it came from
Kokoro v1.0 was published by hexgrad, in January 2025.
It works in Speech, and is recorded as doing text-to-speech (TTS), Speech synthesis.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the hexgrad organisation on Hugging Face.
Understanding the speeds
The median result is around 1,160.3 tokens per second; 818 cards produce text faster than most people read it.
Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.
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.
Training and provenance
Training it took roughly 1.7 × 10²⁰ FLOP of computation, on NVIDIA A100 SXM4 80 GB — a measure of what producing the model cost, not of how fast it answers.
Step by step
How to choose a GPU for Kokoro v1.0
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
The table lists every card that can hold Kokoro v1.0 — around 0.8 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
-
02
Match the context to your actual use
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Kokoro v1.0.
-
03
Choose how far you will compress it
The quantisation column varies by card, because a bigger card holds a more accurate copy of Kokoro v1.0 — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
-
04
Compare tokens per second, not specifications
Sort by speed to see how cards rank for Kokoro v1.0. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 41,320 tok/s.
-
05
Look at the headroom, not just the fit
Tight means Kokoro v1.0 loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
-
06
Check the card from the other side
Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Kokoro v1.0.
Answers
Kokoro v1.0 — common questions
Where can I download Kokoro v1.0?
Its weights are published under the hexgrad organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
How much compute was used to train Kokoro v1.0?
Around 1.7 × 10²⁰ FLOP, on NVIDIA A100 SXM4 80 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Can I run Kokoro v1.0 if it does not fit in my GPU?
It can be split between the card and system memory, but Kokoro v1.0 generates painfully slowly that way. Nothing on this page assumes offloading.
Would two GPUs run Kokoro v1.0 faster?
A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Kokoro v1.0 alone, the case for pairing is weak.
Why does the quantisation differ between cards for Kokoro v1.0?
A larger card holds a more accurate copy. Across the cards that run Kokoro v1.0, 1 compression levels are used; the floor control above pins it to one.
How accurate are these Kokoro v1.0 speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 24,792–66,112 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
What GPU do I need to run Kokoro v1.0?
The smallest card in our catalogue that holds Kokoro v1.0 is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 450 tokens per second. 818 cards in total can run it.
How fast is Kokoro v1.0 on a GPU?
It depends on the card. The quickest we calculate is a B200 at about 41,320 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run Kokoro v1.0 clear that.
How much VRAM does Kokoro v1.0 need?
About 0.8 GB at Q8_0 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.
Can I run Kokoro v1.0 on a 8 GB GPU?
Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.8 GB and generating roughly 7,696 tokens per second — a comfortable fit.
Can I run Kokoro v1.0 on a 12 GB GPU?
Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.8 GB and generating roughly 4,713 tokens per second — a comfortable fit.
Can I run Kokoro v1.0 on a 16 GB GPU?
Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.8 GB and generating roughly 5,836 tokens per second — a comfortable fit.
Can I run Kokoro v1.0 on a 24 GB GPU?
Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.8 GB and generating roughly 6,921 tokens per second — a comfortable fit.
Is Kokoro v1.0 open source?
Its weights are published, so Kokoro v1.0 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 Kokoro v1.0 have?
Kokoro v1.0 has 82M parameters. 82M. 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 Kokoro v1.0?
Kokoro v1.0 was published by hexgrad.
When was Kokoro v1.0 released?
Kokoro v1.0 was published in January 2025.
What is Kokoro v1.0 used for?
Kokoro v1.0 works in Speech, and is recorded as handling text-to-speech (TTS), Speech synthesis. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
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.