Calculate the TPS of the GRID M6-8Q 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 · 11.8 tok/s
Fastest model
Gemma 3 QAT 1B
57.7 tok/s · 1B
Which AI models can run on a GRID M6-8Q?
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 | ||||||
|---|---|---|---|---|---|---|---|
|
57.7
tok/s
20–115 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
57.7
tok/s
20–115 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
57.7
tok/s
20–115 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
57.7
tok/s
20–115 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
57.7
tok/s
20–115 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
57.7
tok/s
20–115 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
53.5
tok/s
19–107 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.5
tok/s
18–105 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.5
tok/s
18–105 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.5
tok/s
18–105 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
52.5
tok/s
18–105 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
17–96 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
17–96 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
17–96 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
48.1
tok/s
17–96 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
47.0
tok/s
16–94 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
46.3
tok/s
16–93 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
44.4
tok/s
16–89 · 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
GRID M6-8Q 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
- GM204
- Architecture
- Maxwell 2.0
- Generation
- GRID(Mx)
- Foundry
- TSMC
- Process size
- 28 nm
- Transistors
- 5.2 billion
- Transistor density
- 13,100 K/mm²
- Die size
- 398 mm²
- Package
- BGA-1745
- Released
- 30 August 2015
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
- 722 MHz
- Boost clock
- 722 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
- 1,536
- Texture mapping units
- 96
- Render output units
- 64
- Streaming multiprocessors
- 12
- L1 cache
- 48 KB
- L2 cache
- 2 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.
- Single precision (FP32)
- 2.2 TFLOPS
- Double precision (FP64)
- 69.3 GFLOPS
- Pixel rate
- 46 GPixel/s
- Texture rate
- 69 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)
- 100 W
- Suggested power supply
- 300 W
- 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
- 5.2
- DirectX
- 12.1
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.8
Listings
Where to buy a GRID M6-8Q
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
Capacity and bandwidth
Memory
8 GB
Bandwidth
160 GB/s
Largest model
Baichuan 1-13B
At 8 GB of GDDR5 the GRID M6-8Q 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.
That comes from a 1.25 GHz memory clock across the bus width above. 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.
In practice that combination tops out at Baichuan 1-13B — 13.3B, compressed to Q3_K_M, generating around 11.8 tokens per second.
The chip and how it was built
The GRID M6-8Q is built on the GM204 graphics processor, using NVIDIA's Maxwell 2.0 architecture, as part of the GRID(Mx) generation.
The chip is manufactured by TSMC, on a 28 nm process, with a die measuring 398 mm², holding 5.2 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 2015, roughly 10 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
FP64
69.3 GFLOPS
Double-precision throughput is 69.3 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 722 MHz at base to 722 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 GRID M6-8Q has 48 KB of L1 cache, backed by 2 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 1,536 shading units, 96 texture mapping units, and 64 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
100 W
The GRID M6-8Q is rated at 100 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 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 GRID M6-8Q
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 GRID M6-8Q
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 GRID M6-8Q
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
The table lists 337 models this GRID M6-8Q 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
Set the context to your real working length. Short questions cost almost nothing; a long document can consume a large share of the card's 8 GB.
-
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
Speeds come with error bars for a reason. The best case here is 57.7 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
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 8 GB available.
-
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 GRID M6-8Q compares.
Answers
GRID M6-8Q — common questions
What type of memory does a GRID M6-8Q 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 GRID M6-8Q?
The GRID M6-8Q is a NVIDIA product, with the chip manufactured by TSMC, on a 28 nm process.
When was the GRID M6-8Q released?
The GRID M6-8Q was released in August 2015.
How much power does a GRID M6-8Q use?
The GRID M6-8Q has a rated board power of 100 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 GRID M6-8Q have?
The GRID M6-8Q has 48 KB of L1 cache, and 2 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.
Does the GRID M6-8Q support CUDA?
Yes. The GRID M6-8Q reports CUDA compute capability 5.2, which predates tensor cores. 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 GRID M6-8Q 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 GRID M6-8Q 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 GRID M6-8Q run a model that does not fit in its memory?
It can be split, with the overflow held in system memory — but that part drags the whole thing down, and none of the 8 GB figures on this page assume it.
Would two GRID M6-8Q cards be twice as fast?
Pairing GRID M6-8Q cards buys headroom rather than pace: 16 GB of combined memory, at roughly the same generation speed as one.
What AI models can a GRID M6-8Q run?
337 of the 679 open-weight language models we track fit on a GRID M6-8Q 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 GRID M6-8Q can run?
The largest model in our catalogue that fits on a GRID M6-8Q is Baichuan 1-13B at 13.3B parameters, compressed to Q3_K_M. It generates roughly 11.8 tokens per second and needs about 7.2 GB of the card's memory.
How many tokens per second does a GRID M6-8Q produce?
It depends on the model. On a GRID M6-8Q the fastest model we track is Gemma 3 QAT 1B at about 57.7 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 GRID M6-8Q run a 7B model?
Yes. For example a GRID M6-8Q runs MetaMath 7B (LLaMa finetune) at Q4_K_M, using about 6.5 GB of memory and generating around 19.0 tokens per second.
Can a GRID M6-8Q run a 13B model?
Yes. For example a GRID M6-8Q runs Gemma 4 12B at Q3_K_M, using about 6.5 GB of memory and generating around 13.0 tokens per second.
How much memory does a GRID M6-8Q have?
A GRID M6-8Q 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 GRID M6-8Q?
The GRID M6-8Q 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.
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.