Tencent Hy3 preview TPS calculator
Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.
Calculated for this model
818 cards we hold specifications for
Smallest card that fits
H200 NVL
141 GB · Q3_K_M · 105 tok/s
Fastest card
B200
147 tok/s · 180 GB
Which GPUs can run Tencent Hy3 preview?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
9 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
147
tok/s
88–236 · low confidence |
B200 NVIDIA | 180 GB | 8,000 GB/s | Jan 2024 | 160.9 GB | Q4_K_M | Tight |
|
105
tok/s
63–168 · low confidence |
H200 NVL NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 126.5 GB | Q3_K_M | Tight |
|
105
tok/s
63–168 · low confidence |
H200 SXM 141 GB NVIDIA | 141 GB | 4,890 GB/s | Nov 2024 | 126.5 GB | Q3_K_M | Tight |
|
92.7
tok/s
56–148 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 229.6 GB | Q6_K | Tight |
|
76.5
tok/s
46–122 · low confidence |
Radeon Instinct MI300X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 160.9 GB | Q4_K_M | Tight |
|
76.5
tok/s
46–122 · low confidence |
Radeon Instinct MI308X AMD | 192 GB | 5,325 GB/s | Dec 2023 | 160.9 GB | Q4_K_M | Tight |
|
74.0
tok/s
44–118 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 229.6 GB | Q6_K | Tight |
|
74.0
tok/s
44–118 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 229.6 GB | Q6_K | Tight |
|
54.2
tok/s
33–87 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 229.6 GB | Q6_K | Tight |
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
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Tencent
- Organisation type
- Industry
- Country
- China
- Published
- 23 April 2026
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation, Question answering
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 295B
- Training data
- tokens
"Today, we are releasing and open-sourcing Hy3 preview. It is a 295B-parameter Mixture-of-Experts (MoE) model, with 21B active parameters, "
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (restricted use)
- Hugging Face
- tencent
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- Discretionary
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Hy3 preview: The First Step in Rebuilding the Hy model
- Last updated
- 22 June 2026
The extremes
The ten fastest GPUs that run Tencent Hy3 preview
Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.
- 01 B200 180 GB · 8,000 GB/s · Q4_K_M 147 tok/s
- 02 H200 NVL 141 GB · 4,890 GB/s · Q3_K_M 105 tok/s
- 03 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q3_K_M 105 tok/s
- 04 B300 288 GB · 8,000 GB/s · Q6_K 92.7 tok/s
- 05 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q4_K_M 76.5 tok/s
- 06 Radeon Instinct MI308X 192 GB · 5,325 GB/s · Q4_K_M 76.5 tok/s
- 07 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q6_K 74.0 tok/s
- 08 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q6_K 74.0 tok/s
- 09 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q6_K 54.2 tok/s
The smallest GPUs that still run Tencent Hy3 preview
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 H200 NVL 141 GB · needs 126.5 GB · Q3_K_M · tight 105 tok/s
- 02 H200 SXM 141 GB 141 GB · needs 126.5 GB · Q3_K_M · tight 105 tok/s
- 03 B200 180 GB · needs 160.9 GB · Q4_K_M · tight 147 tok/s
- 04 Radeon Instinct MI300X 192 GB · needs 160.9 GB · Q4_K_M · tight 76.5 tok/s
- 05 Radeon Instinct MI308X 192 GB · needs 160.9 GB · Q4_K_M · tight 76.5 tok/s
- 06 Radeon Instinct MI325X 256 GB · needs 229.6 GB · Q6_K · tight 54.2 tok/s
- 07 B300 288 GB · needs 229.6 GB · Q6_K · tight 92.7 tok/s
- 08 Radeon Instinct MI350X 288 GB · needs 229.6 GB · Q6_K · tight 74.0 tok/s
- 09 Radeon Instinct MI355X 288 GB · needs 229.6 GB · Q6_K · tight 74.0 tok/s
What the numbers mean
Hardware requirements in practice
Minimum card
H200 NVL
Memory needed
126.5 GB
Fastest
147 tok/s
Tencent Hy3 preview reaches a parameter count of 295B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 9.
The entry point is H200 NVL, with a memory capacity of 141 GB, running it at a compression of Q3_K_M and producing around 105 tokens per second.
At the other end sits B200, generating roughly 147 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.
Where it came from
Tencent Hy3 preview was published by Tencent, in the country recorded as China, during April 2026. The category the publisher falls under is industry.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. On Hugging Face it is published under the organisation tencent.
Understanding the speeds
Half the cards that hold it manage more than 76.5 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 9 of them.
Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.
Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.
How it was trained
Its inclusion criterion: discretionary.
Step by step
How to choose a GPU for Tencent Hy3 preview
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Read the memory figure first
Every card here has been checked against Tencent Hy3 preview, needing around 126.5 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
-
02
Match the context to your actual use
The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Tencent Hy3 preview.
-
03
Decide how much compression you will accept
Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
-
04
Sort by speed
Sort by speed to see how cards rank for Tencent Hy3 preview. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 147 tok/s.
-
05
Read the fit column last
A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Tencent Hy3 preview. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
-
06
See what else that card runs
Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Tencent Hy3 preview.
Answers
Tencent Hy3 preview — common questions
Tencent Hy3 preview— where can I download it?
Its weights are published on Hugging Face, under the organisation tencent. We do not host model files — this site calculates what hardware is needed to run them.
Tencent Hy3 preview— can I run it if it does not fit in my GPU?
It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 45.7 GB. Every figure here assumes the whole model is resident on the card.
Tencent Hy3 preview— would two GPUs run it faster?
A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 9. So a second card is rarely the answer here.
Tencent Hy3 preview— why does the quantisation differ between cards?
Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 3. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Tencent Hy3 preview— how accurate are these speed estimates?
They are calculated from specifications rather than measured, and each carries a range. One example: 88–236 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
Tencent Hy3 preview— what GPU do I need to run it?
The smallest card in our catalogue that holds it is H200 NVL, with a memory capacity of 141 GB. It runs the model at a compression of Q3_K_M using about 126.5 GB, and produces roughly 105 tokens per second. The number of cards able to run it in total: 9.
Tencent Hy3 preview— how fast is it on a GPU?
It depends on the card. The quickest we calculate is B200, at about 147 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 9.
Tencent Hy3 preview— how much VRAM does it need?
It needs about 126.5 GB at a compression of Q3_K_M, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.
Tencent Hy3 preview— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
Tencent Hy3 preview— how many parameters does it have?
It has a parameter count of 295B. "Today, we are releasing and open-sourcing Hy3 preview. It is a 295B-parameter Mixture-of-Experts (MoE) model, with 21B active parameters, ". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Tencent Hy3 preview— who created it?
It was published by Tencent, based in China, an organisation categorised as industry.
Tencent Hy3 preview— when was it released?
It was published in April 2026.
Tencent Hy3 preview— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.