Calculate the TPS of the Xeon Phi 7120X 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
Nemotron 3-Nano-30B-A3B
31.6B · Q3_K_M · 46.0 tok/s
Fastest model
Gemma 3 QAT 1B
96.9 tok/s · 1B
Which AI models can run on a Xeon Phi 7120X?
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.
455 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
96.9
tok/s
58–155 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
96.9
tok/s
58–155 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
96.9
tok/s
58–155 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.9
tok/s
58–155 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.9
tok/s
58–155 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
96.9
tok/s
58–155 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
89.7
tok/s
54–144 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
88.1
tok/s
53–141 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
88.1
tok/s
53–141 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
88.1
tok/s
53–141 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
88.1
tok/s
53–141 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.8
tok/s
48–129 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.8
tok/s
48–129 · low confidence |
LFM2-1.2B ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.8
tok/s
48–129 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.8
tok/s
48–129 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.8
tok/s
48–129 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
78.8
tok/s
47–126 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
77.7
tok/s
47–124 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
74.5
tok/s
45–119 · 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
Xeon Phi 7120X 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
- 352 GB/s
- Memory type
- GDDR5
- Memory bus width
- 512 bit
- Memory clock
- 1.38 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
- Knights Corner
- Architecture
- Knights
- Generation
- Knights Corner(x100)
- Foundry
- Intel
- Process size
- 22 nm
- Transistors
- 5 billion
- Transistor density
- 6,900 K/mm²
- Die size
- 720 mm²
- Released
- 17 June 2013
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
- 1.24 GHz
- Boost clock
- 1.33 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
- 976
- Texture mapping units
- 32
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.
- Single precision (FP32)
- 2.6 TFLOPS
- Texture rate
- 43 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)
- 300 W
- Suggested power supply
- 700 W
- Bus interface
- PCIe 3.0 x16
- Slot width
- Dual-slot
- Dimensions
- 248 mm
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.
- OpenCL
- 1.2
- Shader model
- 5.0
Listings
Where to buy a Xeon Phi 7120X
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
16 GB
Bandwidth
352 GB/s
Largest model
Nemotron 3-Nano-30B-A3B
Xeon Phi 7120X carries 16 GB of GDDR5. 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 352 GB/s across a bus of 512 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.
Bandwidth is clock times bus width, and this card clocks its memory at 1.38 GHz. It is why core counts predict generation speed so poorly.
The practical ceiling is Nemotron 3-Nano-30B-A3B, 31.6B, compressed to Q3_K_M and generating around 46.0 tokens per second.
The chip and how it was built
Xeon Phi 7120X is built on the graphics processor Knights Corner, using the architecture Knights from Intel, as part of the generation Knights Corner(x100).
The chip is manufactured by Intel, on a process of 22 nm, with a die measuring 720 mm², holding 5 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 June 2013, roughly 13.242987479649 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
Clocks run from a base of 1.24 GHz to a boost of 1.33 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
There are 976 shading units, 32 texture mapping 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
300 W
Xeon Phi 7120X is rated at 300 W, and the suggested system power supply is 700 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, measuring 248 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 3.0 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 Xeon Phi 7120X
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 Xeon Phi 7120X
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 Xeon Phi 7120X
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 455 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
Set the context to your real working length. Short questions cost almost nothing, but a long document can consume a large share of 16 GB that is frequently the difference between a model fitting and not.
-
03
Choose how far you will compress
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
The figures are calculated, not measured. The fastest result on this card is 96.9 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 16 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 Xeon Phi 7120X.
Answers
Xeon Phi 7120X — common questions
Xeon Phi 7120X— can it run a model that does not fit in its memory?
It can be split, with the overflow held in system memory beyond the card's 16 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 Xeon Phi 7120X cards be twice as fast?
Pairing them buys headroom rather than pace: 32 GB to work with rather than twice the tokens per second — every figure here is for a single card.
Xeon Phi 7120X— which AI models can it run?
455 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.
Xeon Phi 7120X— 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 46.0 tokens per second and needs about 14.4 GB of the card's memory.
Xeon Phi 7120X— 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 96.9 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.
Xeon Phi 7120X— 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 21.5 tokens per second.
Xeon Phi 7120X— 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 48.9 tokens per second.
Xeon Phi 7120X— 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 51.9 tokens per second.
Xeon Phi 7120X— how much memory does it have?
This card has 16 GB of GDDR5. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 14.4 GB available for a model and its conversation.
Xeon Phi 7120X— what is its memory bandwidth?
Memory bandwidth reaches 352 GB/s across a bus of 512 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.
Xeon Phi 7120X— what type of memory does it use?
It uses GDDR5 clocked at 1.38 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.
Xeon Phi 7120X— who makes it?
This is a product of Intel, with the chip manufactured by Intel, on a process of 22 nm.
Xeon Phi 7120X— when was it released?
It was released in June 2013.
Xeon Phi 7120X— how much power does it use?
Rated board power is 300 W, and the suggested system power supply is 700 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.
Xeon Phi 7120X— 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.
Xeon Phi 7120X— what bus interface does it use?
It uses PCIe 3.0 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.
Xeon Phi 7120X— is it good for running local AI models?
Its memory covers small and mid-sized models, though the largest are out of reach though its bandwidth means generation will feel slow on larger models. In total it runs 455 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
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.