Calculate the TPS of the GeForce RTX 5050 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
Baichuan 1-13B
13.3B · Q3_K_M · 27.6 tok/s
Fastest model
Gemma 3 QAT 1B
136 tok/s · 1B
What AI models can a GeForce RTX 5050 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.
337 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
136
tok/s
115–163 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
136
tok/s
115–163 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
136
tok/s
81–217 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
136
tok/s
81–217 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
136
tok/s
81–217 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
136
tok/s
81–217 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
125
tok/s
75–201 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
123
tok/s
74–197 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
113
tok/s
68–181 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
110
tok/s
94–132 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
109
tok/s
65–174 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
104
tok/s
63–167 · 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
GeForce RTX 5050 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
- 8 GB
- Memory bandwidth
- 320 GB/s
- Memory type
- GDDR6
- Memory bus width
- 128 bit
- Memory clock
- 2.5 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
- GB207
- Architecture
- Blackwell 2.0
- Generation
- GeForce 50
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 16.9 billion
- Transistor density
- 113,400 K/mm²
- Die size
- 149 mm²
- Released
- 1 July 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
- 2.32 GHz
- Boost clock
- 2.57 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
- 2,560
- Texture mapping units
- 80
- Render output units
- 32
- Streaming multiprocessors
- 20
- Tensor cores
- 80
- Ray tracing cores
- 20
- L1 cache
- 128 KB
- L2 cache
- 24 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)
- 13.2 TFLOPS
- Single precision (FP32)
- 13.2 TFLOPS
- Double precision (FP64)
- 205.8 GFLOPS
- Pixel rate
- 82 GPixel/s
- Texture rate
- 206 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)
- 130 W
- Suggested power supply
- 300 W
- Power connectors
- 1x 8-pin
- Bus interface
- PCIe 5.0 x8
- Slot width
- Dual-slot
- Display outputs
- 1x HDMI 2.1b, 3x 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 GeForce RTX 5050
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
8 GB
Bandwidth
320 GB/s
Largest model
Baichuan 1-13B
At 8 GB of GDDR6 the GeForce RTX 5050 is limited to the smaller end of the catalogue. About 7.2 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.
The memory bus moves 320 GB/s across a 128-bit bus. That is the number that governs generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.
The figure is the memory clock — 2.5 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
The biggest thing it holds is Baichuan 1-13B (13.3B) at Q3_K_M compression, for about 27.6 tokens per second.
The chip and how it was built
The GeForce RTX 5050 is built on the GB207 graphics processor, using NVIDIA's Blackwell 2.0 architecture, as part of the GeForce 50 generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 149 mm², holding 16.9 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 July 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
13.2 TFLOPS
FP64
205.8 GFLOPS
Tensor cores
80
On paper the GeForce RTX 5050 reaches 13.2 TFLOPS at half precision and 13.2 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 205.8 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.
The card carries 80 tensor cores across 20 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 2.32 GHz at base to 2.57 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 GeForce RTX 5050 has 128 KB of L1 cache, backed by 24 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 2,560 shading units, 80 texture mapping units, and 32 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
130 W
The GeForce RTX 5050 is rated at 130 W, with a 300 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, 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 5.0 x8. 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 GeForce RTX 5050 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 GeForce RTX 5050
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 RTX 5050
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
Start with the model, not the specification
All 337 models the GeForce RTX 5050 handles are already listed. The search box takes a name or a size such as 27b, which matches on parameter count.
-
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 8 GB it is often what pushes a large model over the edge.
-
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
Take the range as the answer
Speeds come with error bars for a reason. The best case here is 136 tok/s on Gemma 3 QAT 1B, and which inference software you use moves that by thirty to fifty per cent.
-
05
Read the fit verdict last
Compare what each model needs with the 8 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.
-
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 GeForce RTX 5050 compares.
Answers
GeForce RTX 5050 — common questions
What is the largest AI model a GeForce RTX 5050 can run?
The largest model in our catalogue that fits on a GeForce RTX 5050 is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 27.6 tokens per second and needs about 7.2 GB of the card's memory.
How many tokens per second does a GeForce RTX 5050 produce?
It depends on the model. On a GeForce RTX 5050 the fastest model we track is Gemma 3 QAT 1B at about 136 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 GeForce RTX 5050 run a 7B model?
Yes. For example a GeForce RTX 5050 runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 44.7 tokens per second.
Can a GeForce RTX 5050 run a 13B model?
Yes. For example a GeForce RTX 5050 runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 30.6 tokens per second.
How much memory does a GeForce RTX 5050 have?
A GeForce RTX 5050 has 8 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 7.2 GB available for a model and its conversation.
What is the memory bandwidth of a GeForce RTX 5050?
The GeForce RTX 5050 has 320 GB/s of memory bandwidth, across a 128-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 GeForce RTX 5050 use?
It uses GDDR6 clocked at 2.5 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.
Who makes the GeForce RTX 5050?
The GeForce RTX 5050 is a NVIDIA product, with the chip manufactured by TSMC, on a 5 nm process.
When was the GeForce RTX 5050 released?
The GeForce RTX 5050 was released in July 2025.
How much power does a GeForce RTX 5050 use?
The GeForce RTX 5050 has a rated board power of 130 W, and a 300 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 GeForce RTX 5050 have?
The GeForce RTX 5050 has 128 KB of L1 cache, and 24 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 GeForce RTX 5050?
The GeForce RTX 5050 is rated at 13.2 TFLOPS at half precision and 13.2 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 GeForce RTX 5050 have?
The GeForce RTX 5050 has 80 tensor cores across 20 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 GeForce RTX 5050 support CUDA?
Yes. The GeForce RTX 5050 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 GeForce RTX 5050 use?
It uses PCIe 5.0 x8. 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 GeForce RTX 5050 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 337 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a GeForce RTX 5050 run a model that does not fit in its memory?
Only partly. Layers beyond the 8 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 RTX 5050 cards be twice as fast?
No. A second GeForce RTX 5050 doubles the memory to 16 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 GeForce RTX 5050 run?
337 of the 679 open-weight language models we track fit on a GeForce RTX 5050 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.
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.