Calculate the TPS of the Jetson T4000 on local AI models
Every model in our catalogue assessed against this card at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from this card's memory bandwidth and the size of each model once compressed.
Calculated for this card
721 models in our catalogue altogether
Largest model it holds
Qwen3.5-122B-A10B
122B · Q3_K_M · 14.2 tok/s
Fastest model
Gemma 3 QAT 1B
116 tok/s · 1B
Which AI models can run on a Jetson T4000?
Set the inputs, read the answer
More context means more memory for the conversation cache. Speed is for a fresh conversation and does not change with this setting.
Hides models that would only fit by being compressed below this point.
628 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
116
tok/s
98–139 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
116
tok/s
98–139 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
116
tok/s
69–185 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
116
tok/s
69–185 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
116
tok/s
69–185 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
116
tok/s
69–185 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
107
tok/s
64–171 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–168 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–168 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–168 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–168 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.4
tok/s
58–154 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.4
tok/s
58–154 · low confidence |
LFM2-1.2B ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.4
tok/s
58–154 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.4
tok/s
58–154 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.4
tok/s
58–154 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
94.1
tok/s
80–113 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
92.8
tok/s
56–148 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.0
tok/s
53–142 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | 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
Jetson T4000 full specification
Everything on record for this board, ordered by how much it bears on running a language model rather than by how a spec sheet would list it. Memory comes first because it decides the outcome; the rest is context.
Memory
The two specifications that decide what this card can run and how quickly. Capacity sets which models fit; bandwidth sets how many tokens per second they produce once they do.
- Memory size
- 64 GB
- Memory bandwidth
- 273 GB/s
- Memory type
- LPDDR5X
- Memory bus width
- 256 bit
- Memory clock
- 1.07 GHz
The chip
Which processor is on the board and how it was manufactured. A smaller process size generally means more performance for the same power.
- Graphics processor
- GB10B
- Architecture
- Blackwell
- Generation
- Server Blackwell(Bxx)
- Foundry
- TSMC
- Process size
- 3 nm
- Released
- 27 August 2025
Clock speeds
How fast the processor runs. Worth far less here than on a gaming benchmark: generating text is limited by memory bandwidth, so a higher clock barely moves the result.
- Base clock
- 1.67 GHz
- Boost clock
- 2.53 GHz
Processing units
What the chip contains. These drive graphics performance and matter mainly for processing a long prompt rather than for producing the answer.
- Shading units
- 1,536
- Texture mapping units
- 64
- Render output units
- 16
- Streaming multiprocessors
- 12
- Tensor cores
- 64
- Ray tracing cores
- 12
- L1 cache
- 250 KB
- L2 cache
- 50 MB
Theoretical performance
Peak arithmetic rates published for the board. These are ceilings that no real workload reaches, and generating text reaches a small fraction of them because it is limited by memory rather than arithmetic.
- Half precision (FP16)
- 31 TFLOPS
- Single precision (FP32)
- 7.8 TFLOPS
- Double precision (FP64)
- 3.9 TFLOPS
- Pixel rate
- 40 GPixel/s
- Texture rate
- 162 GTexel/s
The board
What it takes to physically install and power the card — the practical constraints that decide whether it fits the machine you already own.
- Power draw (TDP)
- 40 W
- Suggested power supply
- 200 W
- Power connectors
- None
- Bus interface
- PCIe 5.0 x16
- Slot width
- IGP
- Dimensions
- 243 mm × 57 mm
- Display outputs
- 1x HDMI
Software support
Which graphics and compute interfaces the card supports. CUDA compute capability is the one that bears on inference: below 7.0 there are no tensor cores, and modern inference software falls back to slower code paths.
- CUDA compute capability
- 11.0
- OpenCL
- 3.0
Listings
Where to buy a Jetson T4000
No vendor is currently listing this card. Listings come from vendors who publish them here directly — browse the vendor directory to see who is selling what.
What the numbers mean
Why memory is the number that matters here
Memory
64 GB
Bandwidth
273 GB/s
Largest model
Qwen3.5-122B-A10B
Jetson T4000 carries 64 GB of LPDDR5X. That covers the mid-sized models most people actually run. Once the runtime and driver reserve their working space, roughly this much is left: 57.6 GB.
Memory bandwidth reaches 273 GB/s across a bus of 256 bits. Bandwidth is this card's real constraint. Every token requires reading the entire model out of memory, so a large model will feel slow here even when it fits.
That comes from a memory clock of 1.07 GHz. It is why core counts predict generation speed so poorly.
The biggest thing it holds is Qwen3.5-122B-A10B, 122B, compressed to Q3_K_M and generating around 14.2 tokens per second.
The chip and how it was built
Jetson T4000 is built on the graphics processor GB10B, using the architecture Blackwell from NVIDIA, as part of the generation Server Blackwell(Bxx).
The chip is manufactured by TSMC, on a process of 3 nm. A smaller process generally means more performance for the same power, though for language models it matters far less than the memory subsystem.
It was released in August 2025, roughly 1.048466545174 years ago. Inference software support tends to follow hardware by a year or two, so a card of this age generally has mature, well-optimised code paths available to it.
Compute throughput, and why it matters less than it looks
FP16
31 TFLOPS
FP64
3.9 TFLOPS
Tensor cores
64
On paper Jetson T4000 reaches 31 TFLOPS at half precision, and 7.8 TFLOPS at single precision. These are peak figures no real workload sustains, and generating text reaches only a small fraction of them — decoding is limited by memory rather than arithmetic, which is why a card can look enormously powerful here and still produce tokens at an ordinary rate.
Double-precision throughput reaches 3.9 TFLOPS. It has no bearing on running a language model — no inference runtime uses it — but it separates datacentre parts from consumer ones, since the latter deliberately restrict it.
The card carries 64 tensor cores across 12 streaming multiprocessors. These accelerate the matrix arithmetic at the heart of a transformer, and they are what make prompt processing — reading a long document before answering — dramatically faster than it would otherwise be.
Clocks run from a base of 1.67 GHz to a boost of 2.53 GHz. Worth far less here than on a gaming benchmark: raising the clock speeds up the arithmetic, and the arithmetic is not what generation is waiting on.
Cache and processing units
Jetson T4000 has an L1 cache of 250 KB, backed by an L2 cache of 50 MB. Cache absorbs a share of the memory traffic that would otherwise hit the main bus, which is the one place on this page where a number other than bandwidth quietly affects generation speed — a large L2 lets more of the working set stay close to the cores.
There are 1,536 shading units, 64 texture mapping units, and 16 render output units. These drive graphics workloads and contribute to prompt processing, but they sit idle for much of the time a model spends generating a reply.
Power, size and installation
Power draw
40 W
Jetson T4000 is rated at 40 W, and the suggested system power supply is 200 W. Running a language model keeps a card busy in bursts rather than continuously — it draws hard while generating and idles between requests — so sustained draw over a working day is usually well below the rated figure.
The board occupies igp, measuring 243 mm long. Worth checking against the case and power supply already in the machine, since the largest cards need considerably more of both than a typical desktop provides.
It connects over PCIe 5.0 x16. The interface governs how quickly a model is loaded from disk into the card, not how fast it runs once there, so a narrower link costs a few seconds at startup and nothing thereafter.
The extremes
The largest AI models that run on a Jetson T4000
The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.
The fastest AI models on a Jetson T4000
Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.
Step by step
How to work out the tokens per second of a Jetson T4000
You do not have to calculate anything by hand — the gputps.com calculator on this page has already worked it out for every model this card can hold. Reading off the answer takes six steps.
-
01
Find the model in the table
The table lists 628 models this card can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
02
Decide how long your conversations run
Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and against a card holding 64 GB it is often what pushes a large model over the edge.
-
03
Set a minimum quality if you need one
By default the table picks the least-compressed copy that fits. Setting a floor removes models that only qualify through heavy compression.
-
04
Take the range as the answer
Each speed is an estimate for a single conversation, with a range beneath it. The top end here is 116 tok/s on Gemma 3 QAT 1B. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the headroom before you decide
The fit column separates models that just fit from those with room to spare — worth checking before settling on one, against an available 64 GB.
-
06
Cross-check against other hardware
Following a model through to its own page lists all the hardware that can run it, so you can see how it compares against Jetson T4000.
Answers
Jetson T4000 — common questions
Jetson T4000— is it good for running local AI models?
Its memory is large enough for models most desktop hardware cannot touch though its bandwidth means generation will feel slow on larger models. In total it runs 628 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Jetson T4000— can it run a model that does not fit in its memory?
Offloading past the card's 64 GB sit in system memory and run at a fraction of the speed, so a mostly-offloaded model is rarely worth using. Every figure here assumes it is fully resident on the card.
Would two Jetson T4000 cards be twice as fast?
No. A second card doubles the memory to 128 GB of combined memory, at roughly the same generation speed as one.
Jetson T4000— which AI models can it run?
628 of the 721 open-weight language models we track fit on this card and can be run locally. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.
Jetson T4000— what is the largest AI model it can run?
The largest model in our catalogue that fits is Qwen3.5-122B-A10B at 122B parameters, compressed to Q3_K_M. It generates roughly 14.2 tokens per second and needs about 53.1 GB of the card's memory.
Jetson T4000— how many tokens per second does it produce?
It depends on the model. The fastest model we track here is Gemma 3 QAT 1B at about 116 tokens per second, while larger models run proportionally slower because each token requires reading the whole model out of memory once. Speeds are estimates for a single conversation at a time.
Jetson T4000— can it run 7B models?
Yes. For example it runs Gemma 4 E4B at Q8_0, using about 9.8 GB of memory and generating around 25.7 tokens per second.
Jetson T4000— can it run 13B models?
Yes. For example it runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 40.2 tokens per second.
Jetson T4000— can it run 30B models?
Yes. For example it runs ERNIE-4.5-VL-28B-A3B at Q8_0, using about 29.2 GB of memory and generating around 23.0 tokens per second.
Jetson T4000— can it run 70B models?
Yes. For example it runs Qwen3-Coder-Next at Q5_K_M, using about 52.7 GB of memory and generating around 14.4 tokens per second.
Jetson T4000— how much memory does it have?
This card has 64 GB of LPDDR5X. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 57.6 GB available for a model and its conversation.
Jetson T4000— what is its memory bandwidth?
Memory bandwidth reaches 273 GB/s across a bus of 256 bits. This is the single best predictor of how fast it generates text, because producing each token means reading the entire model out of memory once.
Jetson T4000— what type of memory does it use?
It uses LPDDR5X clocked at 1.07 GHz. HBM types are found on datacentre accelerators and carry far more bandwidth than the GDDR used on desktop cards, which is why they generate tokens considerably faster at the same capacity.
Jetson T4000— who makes it?
This is a product of NVIDIA, with the chip manufactured by TSMC, on a process of 3 nm.
Jetson T4000— when was it released?
It was released in August 2025.
Jetson T4000— how much power does it use?
Rated board power is 40 W, and the suggested system power supply is 200 W. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.
Jetson T4000— how much cache does it have?
The L1 cache is 250 KB, and the L2 cache is 50 MB. Cache absorbs part of the memory traffic that would otherwise reach the main bus, so a larger L2 gives a modest lift to generation speed beyond what bandwidth alone predicts.
Jetson T4000— what are its TFLOPS?
It is rated at 31 TFLOPS at half precision and 7.8 TFLOPS at single precision. These are peak arithmetic ceilings rather than achievable rates, and text generation reaches only a small fraction of them because it is limited by memory bandwidth instead.
Jetson T4000— how many tensor cores does it have?
It has 64 tensor cores across 12 streaming multiprocessors. They accelerate the matrix arithmetic a transformer is built from, which mainly speeds up processing a long prompt rather than producing the reply.
Jetson T4000— does it support CUDA?
Yes. It reports CUDA compute capability 11.0. Capability 7.0 and above has tensor cores, which modern inference software uses; below that it falls back to slower code paths for quantised models.
Jetson T4000— what bus interface does it use?
It uses PCIe 5.0 x16. This governs how fast a model is loaded onto the card rather than how fast it runs once loaded, so it costs a few seconds at startup and nothing during generation.
The other direction
Looking at it from the other side?
This page starts from the hardware. If you already know which model you want and need to know what it takes to run it, start from the model instead.