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
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
What AI models can a Jetson T4000 run?
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.
595 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 |
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 |
|
89.0
tok/s
53–142 · low confidence |
Phi-1 ≈ | 1.3B | Oct 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
The Jetson T4000 carries 64 GB of LPDDR5X, which covers the mid-sized models most people actually run — about 57.6 GB of it after the runtime and driver reserve their working space.
At 273 GB/s across a 256-bit bus, 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 1.07 GHz memory clock across the bus width above. Widening the bus and raising the clock are the two levers a manufacturer has, which is why a card with unremarkable cores can still generate quickly.
The biggest thing it holds is Qwen3.5-122B-A10B (122B) at Q3_K_M compression, for about 14.2 tokens per second.
The chip and how it was built
The Jetson T4000 is built on the GB10B graphics processor, using NVIDIA's Blackwell architecture, as part of the Server Blackwell(Bxx) generation.
The chip is manufactured by TSMC, on a 3 nm process. 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. 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 the 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 is 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 1.67 GHz at base to 2.53 GHz boosted. 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
The Jetson T4000 has 250 KB of L1 cache, backed by 50 MB of L2. 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
The Jetson T4000 is rated at 40 W, with a 200 W power supply suggested for the whole system. 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 a 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 a Jetson T4000 can run
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 595 models this Jetson T4000 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 on 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 — 116 tok/s on Gemma 3 QAT 1B at the top end here. 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 against the card's 64 GB before settling on one.
-
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 where the Jetson T4000 sits against the alternatives.
Answers
Jetson T4000 — common questions
Is the Jetson T4000 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 595 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a Jetson T4000 run a model that does not fit in its memory?
Offloading past the card's 64 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
Would two Jetson T4000 cards be twice as fast?
No. A second Jetson T4000 doubles the memory to 128 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.
What AI models can a Jetson T4000 run?
595 of the 679 open-weight language models we track fit on a Jetson T4000 and can be run locally on it. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.
What is the largest AI model a Jetson T4000 can run?
The largest model in our catalogue that fits on a Jetson T4000 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.
How many tokens per second does a Jetson T4000 produce?
It depends on the model. On a Jetson T4000 the fastest model we track 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.
Can a Jetson T4000 run a 7B model?
Yes. For example a Jetson T4000 runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 17.3 tokens per second.
Can a Jetson T4000 run a 13B model?
Yes. For example a Jetson T4000 runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 40.2 tokens per second.
Can a Jetson T4000 run a 30B model?
Yes. For example a Jetson T4000 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.
Can a Jetson T4000 run a 70B model?
Yes. For example a Jetson T4000 runs Qwen3-Coder-Next at Q5_K_M, using about 52.7 GB of memory and generating around 14.4 tokens per second.
How much memory does a Jetson T4000 have?
A Jetson T4000 has 64 GB of LPDDR5X memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 57.6 GB available for a model and its conversation.
What is the memory bandwidth of a Jetson T4000?
The Jetson T4000 has 273 GB/s of memory bandwidth, across a 256-bit memory bus. 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.
What type of memory does a Jetson T4000 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.
Who makes the Jetson T4000?
The Jetson T4000 is a NVIDIA product, with the chip manufactured by TSMC, on a 3 nm process.
When was the Jetson T4000 released?
The Jetson T4000 was released in August 2025.
How much power does a Jetson T4000 use?
The Jetson T4000 has a rated board power of 40 W, and a 200 W system power supply is suggested. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.
How much cache does a Jetson T4000 have?
The Jetson T4000 has 250 KB of L1 cache, and 50 MB of L2 cache. 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.
What are the TFLOPS of a Jetson T4000?
The Jetson T4000 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.
How many tensor cores does a Jetson T4000 have?
The Jetson T4000 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.
Does the Jetson T4000 support CUDA?
Yes. The Jetson T4000 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.
What bus interface does the Jetson T4000 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.