Calculate the TPS of the GeForce GTX 1660 Ti Max-Q 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
Qwen-VL
9.6B · Q3_K_M · 34.3 tok/s
Fastest model
Gemma 3 QAT 1B
122 tok/s · 1B
Which AI models can run on a GeForce GTX 1660 Ti Max-Q?
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.
280 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
122
tok/s
104–146 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
122
tok/s
104–146 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
122
tok/s
73–195 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
122
tok/s
73–195 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
122
tok/s
73–195 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
122
tok/s
73–195 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
111
tok/s
67–177 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
111
tok/s
67–177 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
111
tok/s
67–177 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
111
tok/s
67–177 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
102
tok/s
61–163 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
102
tok/s
61–163 · low confidence |
LFM2-1.2B ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
102
tok/s
61–163 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
102
tok/s
61–163 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
102
tok/s
61–163 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
99.2
tok/s
84–119 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 113k tokens | Q8_0 | Comfortable |
|
97.8
tok/s
59–156 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
93.8
tok/s
56–150 · 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
GeForce GTX 1660 Ti Max-Q 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
- 6 GB
- Memory bandwidth
- 288 GB/s
- Memory type
- GDDR6
- Memory bus width
- 192 bit
- Memory clock
- 1.5 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
- TU116
- Architecture
- Turing
- Generation
- GeForce 16 Mobile
- Foundry
- TSMC
- Process size
- 12 nm
- Transistors
- 6.6 billion
- Transistor density
- 23,200 K/mm²
- Die size
- 284 mm²
- Package
- BGA-2228
- Released
- 23 April 2019
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
- 1.14 GHz
- Boost clock
- 1.34 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
- 96
- Render output units
- 48
- Streaming multiprocessors
- 24
- L1 cache
- 64 KB
- L2 cache
- 1.5 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)
- 8.2 TFLOPS
- Single precision (FP32)
- 4.1 TFLOPS
- Double precision (FP64)
- 128.2 GFLOPS
- Pixel rate
- 64 GPixel/s
- Texture rate
- 128 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 connectors
- None
- Bus interface
- PCIe 3.0 x16
- Slot width
- MXM Module
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
- 7.5
- DirectX
- 12.1
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a GeForce GTX 1660 Ti Max-Q
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
What the memory subsystem means for AI
Memory
6 GB
Bandwidth
288 GB/s
Largest model
Qwen-VL
GeForce GTX 1660 Ti Max-Q carries only 6 GB of GDDR6. That limits it to the smaller end of the catalogue, and a model has to fit entirely inside before it generates anything at all. A runtime actually gets about 5.4 GB.
Memory bandwidth reaches 288 GB/s across a bus of 192 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.
Bandwidth is clock times bus width, and this card clocks its memory at 1.5 GHz. 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.
Put together, the largest model that fits is Qwen-VL, 9.6B, compressed to Q3_K_M and generating around 34.3 tokens per second.
The chip and how it was built
GeForce GTX 1660 Ti Max-Q is built on the graphics processor TU116, using the architecture Turing from NVIDIA, as part of the generation GeForce 16 Mobile.
The chip is manufactured by TSMC, on a process of 12 nm, with a die measuring 284 mm², holding 6.6 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 April 2019, roughly 7.3936737250151 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
8.2 TFLOPS
FP64
128.2 GFLOPS
On paper GeForce GTX 1660 Ti Max-Q reaches 8.2 TFLOPS at half precision, and 4.1 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 128.2 GFLOPS. 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.
Clocks run from a base of 1.14 GHz to a boost of 1.34 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
GeForce GTX 1660 Ti Max-Q has an L1 cache of 64 KB, backed by an L2 cache of 1.5 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, 96 texture mapping units, and 48 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
The board occupies mxm module. 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 GeForce GTX 1660 Ti Max-Q
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 GeForce GTX 1660 Ti Max-Q
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 GeForce GTX 1660 Ti Max-Q
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 280 models the card handles. The search box takes a name or a size such as 27b, which matches on parameter count.
-
02
Match the context to your work
Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and against a card holding 6 GB so the setting is worth getting right.
-
03
Choose how far you will compress
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
Look at the range, not just the number
Each speed is an estimate for a single conversation, with a range beneath it. The top end here is 122 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 6 GB.
-
06
Cross-check against other hardware
Every model name in the table links to its own page, which runs the same calculation across every card we hold. That is where you see whether the right buy is GeForce GTX 1660 Ti Max-Q.
Answers
GeForce GTX 1660 Ti Max-Q — common questions
GeForce GTX 1660 Ti Max-Q— what is its memory bandwidth?
Memory bandwidth reaches 288 GB/s across a bus of 192 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.
GeForce GTX 1660 Ti Max-Q— what type of memory does it use?
It uses GDDR6 clocked at 1.5 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.
GeForce GTX 1660 Ti Max-Q— who makes it?
This is a product of NVIDIA, with the chip manufactured by TSMC, on a process of 12 nm.
GeForce GTX 1660 Ti Max-Q— when was it released?
It was released in April 2019.
GeForce GTX 1660 Ti Max-Q— how much cache does it have?
The L1 cache is 64 KB, and the L2 cache is 1.5 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.
GeForce GTX 1660 Ti Max-Q— what are its TFLOPS?
It is rated at 8.2 TFLOPS at half precision and 4.1 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.
GeForce GTX 1660 Ti Max-Q— does it support CUDA?
Yes. It reports CUDA compute capability 7.5. 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.
GeForce GTX 1660 Ti Max-Q— 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.
GeForce GTX 1660 Ti Max-Q— is it good for running local AI models?
Its memory limits it to smaller models though its bandwidth means generation will feel slow on larger models. In total it runs 280 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
GeForce GTX 1660 Ti Max-Q— 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 6 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 GeForce GTX 1660 Ti Max-Q cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 12 GB of combined memory, at roughly the same generation speed as one.
GeForce GTX 1660 Ti Max-Q— which AI models can it run?
280 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.
GeForce GTX 1660 Ti Max-Q— what is the largest AI model it can run?
The largest model in our catalogue that fits is Qwen-VL at 9.6B parameters, compressed to Q3_K_M. It generates roughly 34.3 tokens per second and needs about 5.4 GB of the card's memory.
GeForce GTX 1660 Ti Max-Q— 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 122 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.
GeForce GTX 1660 Ti Max-Q— can it run 7B models?
Yes. For example it runs Gemma 4 E4B at Q3_K_M, using about 5.2 GB of memory and generating around 73.1 tokens per second.
GeForce GTX 1660 Ti Max-Q— how much memory does it have?
This card has 6 GB of GDDR6. Around a tenth is reserved by the inference runtime and the driver, leaving roughly 5.4 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.