Calculate the TPS of the FirePro W7100 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
679 models in our catalogue altogether
Largest model it holds
Baichuan 1-13B
13.3B · Q3_K_M · 10.8 tok/s
Fastest model
Gemma 3 QAT 1B
52.9 tok/s · 1B
Which AI models can run on a FirePro W7100?
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 | ||||||
|---|---|---|---|---|---|---|---|
|
52.9
tok/s
32–85 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.9
tok/s
32–85 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.9
tok/s
29–78 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
29–77 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
29–77 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
29–77 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
29–77 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.1
tok/s
26–70 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.1
tok/s
26–70 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.1
tok/s
26–70 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.1
tok/s
26–70 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
43.0
tok/s
26–69 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
42.4
tok/s
25–68 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
40.7
tok/s
24–65 · 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
FirePro W7100 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
- 160 GB/s
- Memory type
- GDDR5
- Memory bus width
- 256 bit
- Memory clock
- 1.25 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
- Tonga
- Architecture
- GCN 3.0
- Generation
- FirePro GCN(Wx100)
- Foundry
- TSMC
- Process size
- 28 nm
- Transistors
- 5 billion
- Transistor density
- 13,700 K/mm²
- Die size
- 366 mm²
- Released
- 12 August 2014
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
- 920 MHz
- Boost clock
- 920 MHz
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
- 1,792
- Texture mapping units
- 112
- Render output units
- 32
- L1 cache
- 16 KB
- L2 cache
- 0.5 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)
- 3.3 TFLOPS
- Single precision (FP32)
- 3.3 TFLOPS
- Double precision (FP64)
- 206.1 GFLOPS
- Pixel rate
- 29 GPixel/s
- Texture rate
- 103 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)
- 150 W
- Suggested power supply
- 450 W
- Power connectors
- 1x 6-pin
- Bus interface
- PCIe 3.0 x16
- Slot width
- Single-slot
- Dimensions
- 241 mm
- Display outputs
- 4x DisplayPort 1.2
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.
- DirectX
- 12.0
- OpenGL
- 4.6
- Vulkan
- 1.2
- OpenCL
- 2.1
- Shader model
- 6.5
Listings
Where to buy a FirePro W7100
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
8 GB
Bandwidth
160 GB/s
Largest model
Baichuan 1-13B
At 8 GB of GDDR5 the FirePro W7100 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.
At 160 GB/s across a 256-bit bus, 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 1.25 GHz. Both halves matter, and neither is visible in a gaming benchmark.
The practical ceiling is Baichuan 1-13B at 13.3B, held at Q3_K_M and running at roughly 10.8 tokens per second.
The chip and how it was built
The FirePro W7100 is built on the Tonga graphics processor, using AMD's GCN 3.0 architecture, as part of the FirePro GCN(Wx100) generation.
The chip is manufactured by TSMC, on a 28 nm process, with a die measuring 366 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 August 2014, roughly 11 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
3.3 TFLOPS
FP64
206.1 GFLOPS
On paper the FirePro W7100 reaches 3.3 TFLOPS at half precision and 3.3 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 206.1 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 920 MHz at base to 920 MHz 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 FirePro W7100 has 16 KB of L1 cache, backed by 0.5 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 1,792 shading units, 112 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
150 W
The FirePro W7100 is rated at 150 W, with a 450 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 single-slot, measuring 241 mm long, and needs 1x 6-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 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 FirePro W7100
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 FirePro W7100
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 FirePro W7100
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
Every one of the 337 models this FirePro W7100 runs is in the table above. Search narrows it by name or by size.
-
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 8 GB it is often what pushes a large model over the edge.
-
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
Read the speed and the range
Each speed is an estimate for a single conversation, with a range beneath it — 52.9 tok/s on Gemma 3 QAT 1B at the top end here. The same card and model vary by thirty to fifty per cent between inference runtimes.
-
05
Check the memory column before committing
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
Open the model to compare cards
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 FirePro W7100 compares.
Answers
FirePro W7100 — common questions
What is the largest AI model a FirePro W7100 can run?
The largest model in our catalogue that fits on a FirePro W7100 is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 10.8 tokens per second and needs about 7.2 GB of the card's memory.
How many tokens per second does a FirePro W7100 produce?
It depends on the model. On a FirePro W7100 the fastest model we track is Gemma 3 QAT 1B at about 52.9 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.
Can a FirePro W7100 run a 7B model?
Yes. For example a FirePro W7100 runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 17.4 tokens per second.
Can a FirePro W7100 run a 13B model?
Yes. For example a FirePro W7100 runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 11.9 tokens per second.
How much memory does a FirePro W7100 have?
A FirePro W7100 has 8 GB of GDDR5 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 FirePro W7100?
The FirePro W7100 has 160 GB/s of memory bandwidth, across a 256-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 FirePro W7100 use?
It uses GDDR5 clocked at 1.25 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 FirePro W7100?
The FirePro W7100 is a AMD product, with the chip manufactured by TSMC, on a 28 nm process.
When was the FirePro W7100 released?
The FirePro W7100 was released in August 2014.
How much power does a FirePro W7100 use?
The FirePro W7100 has a rated board power of 150 W, and a 450 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 FirePro W7100 have?
The FirePro W7100 has 16 KB of L1 cache, and 0.5 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 FirePro W7100?
The FirePro W7100 is rated at 3.3 TFLOPS at half precision and 3.3 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.
Does the FirePro W7100 support CUDA?
No. CUDA is NVIDIA-only, and the FirePro W7100 is a AMD card. 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.
What bus interface does the FirePro W7100 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.
Is the FirePro W7100 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 FirePro W7100 run a model that does not fit in its memory?
Offloading past the card's 8 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.
Would two FirePro W7100 cards be twice as fast?
Pairing FirePro W7100 cards buys headroom rather than pace: 16 GB of combined memory, at roughly the same generation speed as one.
What AI models can a FirePro W7100 run?
337 of the 679 open-weight language models we track fit on a FirePro W7100 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.