Calculate the TPS of the RTX 6000D 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
dots.llm1
142B · Q3_K_M · 12.6 tok/s
Fastest model
Gemma 3 QAT 1B
665 tok/s · 1B
What AI models can a RTX 6000D 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.
609 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
665
tok/s
565–798 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
665
tok/s
565–798 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
665
tok/s
399–1,064 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
665
tok/s
399–1,064 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
665
tok/s
399–1,064 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
665
tok/s
399–1,064 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
616
tok/s
369–985 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
604
tok/s
363–967 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
604
tok/s
363–967 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
604
tok/s
363–967 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
604
tok/s
363–967 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
554
tok/s
332–887 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
554
tok/s
332–887 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
554
tok/s
332–887 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
554
tok/s
332–887 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
541
tok/s
460–649 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
533
tok/s
320–853 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
511
tok/s
307–818 · 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
RTX 6000D 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
- 84 GB
- Memory bandwidth
- 1,570 GB/s
- Memory type
- GDDR7
- Memory bus width
- 448 bit
- Memory clock
- 1.75 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
- GB202
- Architecture
- Blackwell 2.0
- Generation
- Blackwell PRO W(x000)
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 92.2 billion
- Transistor density
- 122,900 K/mm²
- Die size
- 750 mm²
- Released
- 18 March 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
- 1.59 GHz
- Boost clock
- 2.43 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
- 19,968
- Texture mapping units
- 624
- Render output units
- 192
- Streaming multiprocessors
- 156
- Tensor cores
- 624
- Ray tracing cores
- 156
- L1 cache
- 128 KB
- L2 cache
- 128 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)
- 97 TFLOPS
- Single precision (FP32)
- 97 TFLOPS
- Double precision (FP64)
- 1.5 TFLOPS
- Pixel rate
- 467 GPixel/s
- Texture rate
- 1,516 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)
- 600 W
- Suggested power supply
- 1,000 W
- Power connectors
- 1x 16-pin
- Bus interface
- PCIe 5.0 x16
- Slot width
- Dual-slot
- Dimensions
- 304 mm × 40 mm
- Display outputs
- 4x DisplayPort 2.1b
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
- 12.0
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a RTX 6000D
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
Capacity and bandwidth
Memory
84 GB
Bandwidth
1,570 GB/s
Largest model
dots.llm1
With 84 GB of GDDR7, the RTX 6000D is in the class of hardware that holds the largest open-weight models without splitting them across machines. Roughly 75.6 GB of that is reachable by an inference runtime once the driver takes its share.
Bandwidth is 1,570 GB/s across a 448-bit bus. Generating a token means reading every weight once, so that figure sets the pace more than any other number here, and at this level text arrives faster than most people read.
The figure is the memory clock — 1.75 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
In practice that combination tops out at dots.llm1 — 142B, compressed to Q3_K_M, generating around 12.6 tokens per second.
The chip and how it was built
The RTX 6000D is built on the GB202 graphics processor, using NVIDIA's Blackwell 2.0 architecture, as part of the Blackwell PRO W(x000) generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 750 mm², holding 92.2 billion transistors. 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 March 2025, roughly 1 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
97 TFLOPS
FP64
1.5 TFLOPS
Tensor cores
624
On paper the RTX 6000D reaches 97 TFLOPS at half precision and 97 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 1.5 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 624 tensor cores across 156 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 1.59 GHz at base to 2.43 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 RTX 6000D has 128 KB of L1 cache, backed by 128 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 19,968 shading units, 624 texture mapping units, and 192 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
600 W
The RTX 6000D is rated at 600 W, with a 1,000 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 dual-slot, measuring 304 mm long, and needs 1x 16-pin. 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 RTX 6000D 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 RTX 6000D
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 RTX 6000D
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
Search for the model you want
The table lists 609 models this RTX 6000D can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
02
Match the context to your work
Longer conversations cost memory on top of the weights. With 84 GB to work in, that is frequently the difference between a model fitting and not.
-
03
Pin the comparison to one quality level
By default the table picks the least-compressed copy that fits. Setting a floor removes models that only qualify through heavy compression.
-
04
Read the speed and the range
Each speed is an estimate for a single conversation, with a range beneath it — 665 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 84 GB before settling on one.
-
06
Check the same model from the other side
Each model page repeats this calculation for the whole catalogue. Worth a look before deciding: it shows what else runs the same model, and how the RTX 6000D compares.
Answers
RTX 6000D — common questions
What is the memory bandwidth of a RTX 6000D?
The RTX 6000D has 1,570 GB/s of memory bandwidth, across a 448-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 RTX 6000D use?
It uses GDDR7 clocked at 1.75 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 RTX 6000D?
The RTX 6000D is a NVIDIA product, with the chip manufactured by TSMC, on a 5 nm process.
When was the RTX 6000D released?
The RTX 6000D was released in March 2025.
How much power does a RTX 6000D use?
The RTX 6000D has a rated board power of 600 W, and a 1,000 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 RTX 6000D have?
The RTX 6000D has 128 KB of L1 cache, and 128 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 RTX 6000D?
The RTX 6000D is rated at 97 TFLOPS at half precision and 97 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 RTX 6000D have?
The RTX 6000D has 624 tensor cores across 156 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 RTX 6000D support CUDA?
Yes. The RTX 6000D reports CUDA compute capability 12.0. 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 RTX 6000D 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.
Is the RTX 6000D good for running local AI models?
Its memory is large enough for models most desktop hardware cannot touch and its bandwidth is high enough to generate text faster than most people read. In total it runs 609 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a RTX 6000D run a model that does not fit in its memory?
Offloading past the card's 84 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
Would two RTX 6000D cards be twice as fast?
Pairing RTX 6000D cards buys headroom rather than pace: 168 GB of combined memory, at roughly the same generation speed as one.
What AI models can a RTX 6000D run?
609 of the 679 open-weight language models we track fit on a RTX 6000D 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 RTX 6000D can run?
The largest model in our catalogue that fits on a RTX 6000D is dots.llm1 at 142B parameters, compressed to Q3_K_M. It generates roughly 12.6 tokens per second and needs about 70.1 GB of the card's memory.
How many tokens per second does a RTX 6000D produce?
It depends on the model. On a RTX 6000D the fastest model we track is Gemma 3 QAT 1B at about 665 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 RTX 6000D run a 7B model?
Yes. For example a RTX 6000D runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 99.2 tokens per second.
Can a RTX 6000D run a 13B model?
Yes. For example a RTX 6000D runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 231 tokens per second.
Can a RTX 6000D run a 30B model?
Yes. For example a RTX 6000D runs ERNIE-4.5-VL-28B-A3B at Q8_0, using about 29.2 GB of memory and generating around 132 tokens per second.
Can a RTX 6000D run a 70B model?
Yes. For example a RTX 6000D runs Qwen3-Coder-Next at Q6_K, using about 62.0 GB of memory and generating around 67.1 tokens per second.
How much memory does a RTX 6000D have?
A RTX 6000D has 84 GB of GDDR7 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 75.6 GB available for a model and its conversation.
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.