Calculate the TPS of the H800 SXM5 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 · 27.0 tok/s
Fastest model
Gemma 3 QAT 1B
1,423 tok/s · 1B
What AI models can a H800 SXM5 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 | ||||||
|---|---|---|---|---|---|---|---|
|
1,423
tok/s
1,210–1,708 |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
1,423
tok/s
1,210–1,708 |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
1,423
tok/s
854–2,277 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,423
tok/s
854–2,277 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,423
tok/s
854–2,277 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,423
tok/s
854–2,277 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,318
tok/s
791–2,108 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,294
tok/s
776–2,070 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,294
tok/s
776–2,070 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,294
tok/s
776–2,070 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,294
tok/s
776–2,070 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,186
tok/s
712–1,897 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,186
tok/s
712–1,897 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,186
tok/s
712–1,897 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,186
tok/s
712–1,897 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,157
tok/s
983–1,388 |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
1,141
tok/s
684–1,825 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
1,095
tok/s
657–1,751 · 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
H800 SXM5 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
- 80 GB
- Memory bandwidth
- 3,360 GB/s
- Memory type
- HBM3
- Memory bus width
- 5,120 bit
- Memory clock
- 1.31 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
- GH100
- Architecture
- Hopper
- Generation
- Server Hopper(Hxx)
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 80 billion
- Transistor density
- 98,300 K/mm²
- Die size
- 814 mm²
- Released
- 21 March 2023
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
- 1.1 GHz
- Boost clock
- 1.76 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
- 16,896
- Texture mapping units
- 528
- Render output units
- 24
- Streaming multiprocessors
- 132
- Tensor cores
- 528
- L1 cache
- 250 KB
- L2 cache
- 50 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)
- 237.2 TFLOPS
- Single precision (FP32)
- 59.3 TFLOPS
- Double precision (FP64)
- 29.7 TFLOPS
- Pixel rate
- 42 GPixel/s
- Texture rate
- 927 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)
- 700 W
- Suggested power supply
- 1,100 W
- Power connectors
- 8-pin EPS
- Bus interface
- PCIe 5.0 x16
- Slot width
- SXM 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
- 9.0
- OpenCL
- 3.0
Listings
Where to buy a H800 SXM5
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
80 GB
Bandwidth
3,360 GB/s
Largest model
dots.llm1
With 80 GB of HBM3, the H800 SXM5 is in the class of hardware that holds the largest open-weight models without splitting them across machines. Roughly 72 GB of that is reachable by an inference runtime once the driver takes its share.
Its 3,360 GB/s across a 5,120-bit bus is at the top of what exists. Since each token means reading the whole model out of memory once, that translates almost directly into generation speed — this card is bandwidth-rich enough that model size stops being the limiting factor long before the bus does.
Bandwidth is clock times bus width, and this card clocks its memory at 1.31 GHz. Both halves matter, and neither is visible in a gaming benchmark.
In practice that combination tops out at dots.llm1 — 142B, compressed to Q3_K_M, generating around 27.0 tokens per second.
The chip and how it was built
The H800 SXM5 is built on the GH100 graphics processor, using NVIDIA's Hopper architecture, as part of the Server Hopper(Hxx) generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 814 mm², holding 80 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 2023, roughly 3 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
237.2 TFLOPS
FP64
29.7 TFLOPS
Tensor cores
528
On paper the H800 SXM5 reaches 237.2 TFLOPS at half precision and 59.3 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 29.7 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 528 tensor cores across 132 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 1.1 GHz at base to 1.76 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 H800 SXM5 has 250 KB of L1 cache, backed by 50 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 16,896 shading units, 528 texture mapping units, and 24 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
700 W
The H800 SXM5 is rated at 700 W, with a 1,100 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 sxm module, and needs 8-pin EPS. 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 H800 SXM5 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 H800 SXM5
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 H800 SXM5
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 609 models this H800 SXM5 can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.
-
02
Set the context length you will actually use
Drag the slider to the conversation length you plan to work at. The cache grows with the conversation, and on 80 GB it is often what pushes a large model over the edge.
-
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. 1,423 tok/s on Gemma 3 QAT 1B is the fastest result on this card, and like every row it carries a range that reflects how much the runtime matters.
-
05
Read the fit verdict last
A tight fit runs but leaves no room to raise the context later; comfortable has headroom. The memory column shows what each model needs against the 80 GB available.
-
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 where the H800 SXM5 sits against the alternatives.
Answers
H800 SXM5 — common questions
Would two H800 SXM5 cards be twice as fast?
Capacity adds, throughput does not. Two of them give you 160 GB to work with rather than twice the tokens per second — every figure here is for a single H800 SXM5.
What AI models can a H800 SXM5 run?
609 of the 679 open-weight language models we track fit on a H800 SXM5 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 H800 SXM5 can run?
The largest model in our catalogue that fits on a H800 SXM5 is dots.llm1 at 142B parameters, compressed to Q3_K_M. It generates roughly 27.0 tokens per second and needs about 70.1 GB of the card's memory.
How many tokens per second does a H800 SXM5 produce?
It depends on the model. On a H800 SXM5 the fastest model we track is Gemma 3 QAT 1B at about 1,423 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 H800 SXM5 run a 7B model?
Yes. For example a H800 SXM5 runs Multi-Token Prediction 7B at Q8_0, using about 7.9 GB of memory and generating around 212 tokens per second.
Can a H800 SXM5 run a 13B model?
Yes. For example a H800 SXM5 runs DeepSeekMoE-16B at Q8_0, using about 17.5 GB of memory and generating around 494 tokens per second.
Can a H800 SXM5 run a 30B model?
Yes. For example a H800 SXM5 runs ERNIE-4.5-VL-28B-A3B at Q8_0, using about 29.2 GB of memory and generating around 282 tokens per second.
Can a H800 SXM5 run a 70B model?
Yes. For example a H800 SXM5 runs Qwen3-Coder-Next at Q6_K, using about 62.0 GB of memory and generating around 144 tokens per second.
How much memory does a H800 SXM5 have?
A H800 SXM5 has 80 GB of HBM3 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 72 GB available for a model and its conversation.
What is the memory bandwidth of a H800 SXM5?
The H800 SXM5 has 3,360 GB/s of memory bandwidth, across a 5,120-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 H800 SXM5 use?
It uses HBM3 clocked at 1.31 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 H800 SXM5?
The H800 SXM5 is a NVIDIA product, with the chip manufactured by TSMC, on a 5 nm process.
When was the H800 SXM5 released?
The H800 SXM5 was released in March 2023.
How much power does a H800 SXM5 use?
The H800 SXM5 has a rated board power of 700 W, and a 1,100 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 H800 SXM5 have?
The H800 SXM5 has 250 KB of L1 cache, and 50 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 H800 SXM5?
The H800 SXM5 is rated at 237.2 TFLOPS at half precision and 59.3 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 H800 SXM5 have?
The H800 SXM5 has 528 tensor cores across 132 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 H800 SXM5 support CUDA?
Yes. The H800 SXM5 reports CUDA compute capability 9.0. 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 H800 SXM5 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 H800 SXM5 good for running local AI models?
Its memory is large enough for models most desktop hardware cannot touch and its bandwidth puts it among the fastest hardware available for generation. 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 H800 SXM5 run a model that does not fit in its memory?
Only partly. Layers beyond the 80 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.
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.