Calculate the TPS of the Radeon R9 M395X Mac Edition on local AI models

AMD 4 GB GDDR5 175 GB/s May 2015

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

97 models it can run

679 models in our catalogue altogether

Largest model it holds

DeciLM 6B

5.7B · Q3_K_M · 27.3 tok/s

Fastest model

Gemma 3 QAT 1B

57.7 tok/s · 1B

Which AI models can run on a Radeon R9 M395X Mac Edition?

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.

97 models match

Calculating
Quantisation Fit
57.7 tok/s

35–92 · low confidence

Gemma 3 1B 1B Mar 2025 1.8 GB 33k tokens Q8_0 Comfortable
57.7 tok/s

35–92 · low confidence

Gemma 3 QAT 1B 1B Apr 2025 1.8 GB 33k tokens Q8_0 Comfortable
57.7 tok/s

35–92 · low confidence

HGRN 1B (WT 103) ≈ 1B Nov 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
57.7 tok/s

35–92 · low confidence

LLama 3..2 Typhoon 2 1B ≈ 1B Dec 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
57.7 tok/s

35–92 · low confidence

OLMo-1B ≈ 1B Feb 2024 1.8 GB 131k tokens ? Q8_0 Comfortable
57.7 tok/s

35–92 · low confidence

Pythia-1b ≈ 1B Apr 2023 1.8 GB 131k tokens ? Q8_0 Comfortable
53.4 tok/s

32–86 · low confidence

OpenELM-1.1B ≈ 1.1B May 2024 1.9 GB 131k tokens ? Q8_0 Comfortable
52.5 tok/s

31–84 · low confidence

DeciCoder-1B ≈ 1.1B Aug 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
52.5 tok/s

31–84 · low confidence

SantaCoder ≈ 1.1B Jan 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
52.5 tok/s

31–84 · low confidence

TinyLlama-1.1B (1T token checkpoint) ≈ 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
52.5 tok/s

31–84 · low confidence

TinyLlama-1.1B (3T token checkpoint) ≈ 1.1B Oct 2023 1.9 GB 131k tokens ? Q8_0 Comfortable
48.1 tok/s

29–77 · low confidence

EXAONE 4.0 (1.2B) ≈ 1.2B Jul 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
48.1 tok/s

29–77 · low confidence

MinerU2.5 ≈ 1.2B Sep 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
48.1 tok/s

29–77 · low confidence

Pleias 1.0 1.2B ≈ 1.2B Dec 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
48.1 tok/s

29–77 · low confidence

Pleias-RAG-1B ≈ 1.2B Apr 2025 2.0 GB 131k tokens ? Q8_0 Comfortable
46.9 tok/s

28–75 · low confidence

Llama 3.2 1B 1.2B Sep 2024 2.2 GB 54k tokens Q8_0 Comfortable
46.3 tok/s

28–74 · low confidence

MiniCPM-1.2B ≈ 1.2B Jun 2024 2.0 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

DeepSeek Coder 1.3B ≈ 1.3B Jan 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

DeepSeek-VL-1.3B ≈ 1.3B Mar 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

DigiRL ≈ 1.3B Jun 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

GLA Transformer 1.3B ≈ 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

Janus 1.3B ≈ 1.3B Oct 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

Kosmos-2.5 ≈ 1.3B Aug 2024 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · low confidence

Otter ≈ 1.3B May 2023 2.1 GB 131k tokens ? Q8_0 Comfortable
44.4 tok/s

27–71 · 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

Radeon R9 M395X Mac Edition 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
4 GB
Memory bandwidth
175 GB/s
Memory type
GDDR5
Memory bus width
256 bit
Memory clock
1.37 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
Amethyst
Architecture
GCN 3.0
Generation
Gem System(R9 M300)
Foundry
TSMC
Process size
28 nm
Transistors
5 billion
Transistor density
13,700 K/mm²
Die size
366 mm²
Released
5 May 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
909 MHz
Boost clock
909 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
2,048
Texture mapping units
128
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)
3.7 TFLOPS
Single precision (FP32)
3.7 TFLOPS
Double precision (FP64)
232.7 GFLOPS
Pixel rate
29 GPixel/s
Texture rate
116 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)
250 W
Power connectors
None
Bus interface
MXM-B (3.0)
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.

DirectX
12.0
OpenGL
4.6
Vulkan
1.2
OpenCL
2.1
Shader model
6.5

Listings

Where to buy a Radeon R9 M395X Mac Edition

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

Why memory is the number that matters here

Memory

4 GB

Bandwidth

175 GB/s

Largest model

DeciLM 6B

At 4 GB of GDDR5 the Radeon R9 M395X Mac Edition is limited to the smaller end of the catalogue. About 3.6 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.

At 175 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 1.37 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.

Put together, the largest model that fits is DeciLM 6B at 5.7B, running Q3_K_M and producing around 27.3 tokens per second.

The chip and how it was built

The Radeon R9 M395X Mac Edition is built on the Amethyst graphics processor, using AMD's GCN 3.0 architecture, as part of the Gem System(R9 M300) 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 May 2015, 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

3.7 TFLOPS

FP64

232.7 GFLOPS

On paper the Radeon R9 M395X Mac Edition reaches 3.7 TFLOPS at half precision and 3.7 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 232.7 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 909 MHz at base to 909 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 Radeon R9 M395X Mac Edition 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 2,048 shading units, 128 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

250 W

The Radeon R9 M395X Mac Edition is rated at 250 W. 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 MXM-B (3.0). 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 Radeon R9 M395X Mac Edition

The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.

  1. 01 Qwen3.5-4B 4B · Q5_K_M · Feb 2026 25.8 tok/s
  2. 02 Voxtral Mini 4.7B · Q4_K_M · Jul 2025 28.4 tok/s
  3. 03 Typhoon 2.1 Gemma 4B 4B · Q4_K_M · May 2025 33.3 tok/s
  4. 04 Qwen3-4B 4B · Q3_K_M · Apr 2025 38.9 tok/s
  5. 05 Gemma 3 QAT 4B 4B · Q4_K_M · Apr 2025 33.3 tok/s
  6. 06 Gemma 3 4B 4B · Q4_K_M · Mar 2025 33.3 tok/s
  7. 07 Phi-4-Multimodal 5.6B · Q3_K_M · Mar 2025 27.8 tok/s
  8. 08 Minitron 4B 4.2B · Q4_K_M · Nov 2024 31.7 tok/s
  9. 09 XVERSE-MoE-A4.2B 4.2B · Q4_K_M · Apr 2024 31.7 tok/s
  10. 10 DeciLM 6B 5.7B · Q3_K_M · Sep 2023 27.3 tok/s

The fastest AI models on a Radeon R9 M395X Mac Edition

Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.

  1. 01 Gemma 3 QAT 1B 1B · Q8_0 · 1.8 GB 57.7 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 57.7 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 57.7 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 57.7 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 57.7 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 57.7 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 53.4 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 52.5 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 52.5 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 52.5 tok/s

Step by step

How to work out the tokens per second of a Radeon R9 M395X Mac Edition

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.

  1. 01

    Find the model in the table

    The table lists 97 models this Radeon R9 M395X Mac Edition can run. Search by name, or by size — typing 27b matches on the parameter count even when the name never states it.

  2. 02

    Set the context length you will actually use

    Longer conversations cost memory on top of the weights. With 4 GB to work in, that is frequently the difference between a model fitting and not.

  3. 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.

  4. 04

    Look at the range, not just the number

    The figures are calculated, not measured. 57.7 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.

  5. 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 4 GB available.

  6. 06

    Check the same model from the other side

    Every model name in the table links to its own page, which runs the same calculation across every card we hold. That is where you see whether the Radeon R9 M395X Mac Edition is the right buy for it or merely a card that fits.

Answers

Radeon R9 M395X Mac Edition — common questions

01

When was the Radeon R9 M395X Mac Edition released?

The Radeon R9 M395X Mac Edition was released in May 2015.

02

How much power does a Radeon R9 M395X Mac Edition use?

The Radeon R9 M395X Mac Edition has a rated board power of 250 W. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.

03

How much cache does a Radeon R9 M395X Mac Edition have?

The Radeon R9 M395X Mac Edition 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.

04

What are the TFLOPS of a Radeon R9 M395X Mac Edition?

The Radeon R9 M395X Mac Edition is rated at 3.7 TFLOPS at half precision and 3.7 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.

05

Does the Radeon R9 M395X Mac Edition support CUDA?

No. CUDA is NVIDIA-only, and the Radeon R9 M395X Mac Edition 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.

06

What bus interface does the Radeon R9 M395X Mac Edition use?

It uses MXM-B (3.0). 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.

07

Is the Radeon R9 M395X Mac Edition 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 97 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.

08

Can a Radeon R9 M395X Mac Edition 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 4 GB figures on this page assume it.

09

Would two Radeon R9 M395X Mac Edition cards be twice as fast?

Capacity adds, throughput does not. Two of them give you 8 GB to work with rather than twice the tokens per second — every figure here is for a single Radeon R9 M395X Mac Edition.

10

What AI models can a Radeon R9 M395X Mac Edition run?

97 of the 679 open-weight language models we track fit on a Radeon R9 M395X Mac Edition 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.

11

What is the largest AI model a Radeon R9 M395X Mac Edition can run?

The largest model in our catalogue that fits on a Radeon R9 M395X Mac Edition is DeciLM 6B at 5.7B parameters, compressed to Q3_K_M. It generates roughly 27.3 tokens per second and needs about 3.5 GB of the card's memory.

12

How many tokens per second does a Radeon R9 M395X Mac Edition produce?

It depends on the model. On a Radeon R9 M395X Mac Edition 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.

13

How much memory does a Radeon R9 M395X Mac Edition have?

A Radeon R9 M395X Mac Edition has 4 GB of GDDR5 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 3.6 GB available for a model and its conversation.

14

What is the memory bandwidth of a Radeon R9 M395X Mac Edition?

The Radeon R9 M395X Mac Edition has 175 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.

15

What type of memory does a Radeon R9 M395X Mac Edition use?

It uses GDDR5 clocked at 1.37 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.

16

Who makes the Radeon R9 M395X Mac Edition?

The Radeon R9 M395X Mac Edition is a AMD product, with the chip manufactured by TSMC, on a 28 nm process.

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.

All GPUs