Calculate the TPS of the Data Center GPU Flex 170 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
679 models in our catalogue altogether
Largest model it holds
Nemotron 3-Nano-30B-A3B
31.6B · Q3_K_M · 66.9 tok/s
Fastest model
Gemma 3 QAT 1B
141 tok/s · 1B
Which AI models can run on a Data Center GPU Flex 170?
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.
432 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
141
tok/s
85–226 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
141
tok/s
85–226 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
141
tok/s
85–226 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
141
tok/s
85–226 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
141
tok/s
85–226 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
141
tok/s
85–226 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
131
tok/s
78–209 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
128
tok/s
77–205 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
117
tok/s
70–188 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
117
tok/s
70–188 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
117
tok/s
70–188 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
117
tok/s
70–188 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
115
tok/s
69–183 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
108
tok/s
65–173 · 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
Data Center GPU Flex 170 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
- 16 GB
- Memory bandwidth
- 512 GB/s
- Memory type
- GDDR6
- Memory bus width
- 256 bit
- Memory clock
- 2 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
- DG2-512
- Architecture
- Xe-HPG
- Generation
- Data Center GPU(Arctic Sound)
- Foundry
- TSMC
- Process size
- 6 nm
- Transistors
- 21.7 billion
- Transistor density
- 53,400 K/mm²
- Die size
- 406 mm²
- Released
- 24 August 2022
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
- 1.95 GHz
- Boost clock
- 2.05 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
- 4,096
- Texture mapping units
- 256
- Render output units
- 128
- Ray tracing cores
- 32
- L2 cache
- 16 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)
- 33.6 TFLOPS
- Single precision (FP32)
- 16.8 TFLOPS
- Pixel rate
- 262 GPixel/s
- Texture rate
- 525 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)
- 150 W
- Suggested power supply
- 450 W
- Power connectors
- 1x 8-pin
- Bus interface
- PCIe 4.0 x16
- Slot width
- Dual-slot
- Display outputs
- 1x HDMI 2.1, 3x DisplayPort 2.0
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.
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.6
Listings
Where to buy a Data Center GPU Flex 170
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
Memory: the specification that decides everything
Memory
16 GB
Bandwidth
512 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
Data Center GPU Flex 170 carries 16 GB of GDDR6. That reaches comfortably into small and mid-sized models, though the largest stay out of reach without splitting them. Driver overhead leaves roughly 14.4 GB.
Memory bandwidth reaches 512 GB/s across a bus of 256 bits. That is the number governing generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.
That comes from a memory clock of 2 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The practical ceiling is Nemotron 3-Nano-30B-A3B, 31.6B, compressed to Q3_K_M and generating around 66.9 tokens per second.
The chip and how it was built
Data Center GPU Flex 170 is built on the graphics processor DG2-512, using the architecture Xe-HPG from Intel, as part of the generation Data Center GPU(Arctic Sound).
The chip is manufactured by TSMC, on a process of 6 nm, with a die measuring 406 mm², holding 21.7 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 August 2022, roughly 3.9365713520627 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
33.6 TFLOPS
On paper Data Center GPU Flex 170 reaches 33.6 TFLOPS at half precision, and 16.8 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.
Clocks run from a base of 1.95 GHz to a boost of 2.05 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
backed by an L2 cache of 16 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 4,096 shading units, 256 texture mapping units, and 128 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
150 W
Data Center GPU Flex 170 is rated at 150 W, and the suggested system power supply is 450 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 dual-slot, and needs 1x 8-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 4.0 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 Data Center GPU Flex 170
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 Data Center GPU Flex 170
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 Data Center GPU Flex 170
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 432 models the card handles. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Set the context length you will actually use
Longer conversations cost memory on top of the weights. Against 16 GB it is often what pushes a large model over the edge.
-
03
Pin the comparison to one quality level
Each model is shown at the best compression this card can hold. A minimum quality hides the ones that only fit by being squeezed further than you would accept.
-
04
Read the speed and the range
The figures are calculated, not measured. The fastest result on this card is 141 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 memory column before committing
The fit column separates models that just fit from those with room to spare — worth checking before settling on one, against an available 16 GB.
-
06
Open the model to compare cards
Following a model through to its own page lists all the hardware that can run it, so you can see how it compares against Data Center GPU Flex 170.
Answers
Data Center GPU Flex 170 — common questions
Data Center GPU Flex 170— can it run 13B models?
Yes. For example it runs DeepSeekMoE-16B at Q6_K, using about 13.7 GB of memory and generating around 71.1 tokens per second.
Data Center GPU Flex 170— can it run 30B models?
Yes. For example it runs ERNIE-4.5-VL-28B-A3B at Q3_K_M, using about 12.9 GB of memory and generating around 75.5 tokens per second.
Data Center GPU Flex 170— how much memory does it have?
This card has 16 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 14.4 GB available for a model and its conversation.
Data Center GPU Flex 170— what is its memory bandwidth?
Memory bandwidth reaches 512 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.
Data Center GPU Flex 170— what type of memory does it use?
It uses GDDR6 clocked at 2 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.
Data Center GPU Flex 170— who makes it?
This is a product of Intel, with the chip manufactured by TSMC, on a process of 6 nm.
Data Center GPU Flex 170— when was it released?
It was released in August 2022.
Data Center GPU Flex 170— how much power does it use?
Rated board power is 150 W, and the suggested system power supply is 450 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.
Data Center GPU Flex 170— how much cache does it have?
and the L2 cache is 16 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.
Data Center GPU Flex 170— what are its TFLOPS?
It is rated at 33.6 TFLOPS at half precision and 16.8 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.
Data Center GPU Flex 170— does it support CUDA?
No. CUDA is NVIDIA-only, and this is a card from Intel. It runs language models through ROCm, Vulkan or Metal depending on the software, which are less mature than the CUDA path — our estimates apply a penalty for that.
Data Center GPU Flex 170— what bus interface does it use?
It uses PCIe 4.0 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.
Data Center GPU Flex 170— is it good for running local AI models?
Its memory covers small and mid-sized models, though the largest are out of reach and its bandwidth gives usable, if unspectacular, generation speeds. In total it runs 432 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Data Center GPU Flex 170— can it run a model that does not fit in its memory?
Only partly. Layers beyond the card's 16 GB drags the whole thing down, and none of the figures on this page assume it.
Would two Data Center GPU Flex 170 cards be twice as fast?
Pairing them buys headroom rather than pace: 32 GB of combined memory, at roughly the same generation speed as one.
Data Center GPU Flex 170— which AI models can it run?
432 of the 679 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.
Data Center GPU Flex 170— what is the largest AI model it can run?
The largest model in our catalogue that fits is Nemotron 3-Nano-30B-A3B at 31.6B parameters, compressed to Q3_K_M. It generates roughly 66.9 tokens per second and needs about 14.4 GB of the card's memory.
Data Center GPU Flex 170— 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 141 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.
Data Center GPU Flex 170— can it run 7B models?
Yes. For example it runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 21.0 tokens per second.
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.