Calculate the TPS of the Radeon R9 M365X on local AI models

AMD 4 GB GDDR5 72 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 · 11.3 tok/s

Fastest model

Gemma 3 QAT 1B

23.8 tok/s · 1B

Which AI models can run on a Radeon R9 M365X?

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
23.8 tok/s

14–38 · low confidence

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

14–38 · low confidence

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

14–38 · low confidence

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

14–38 · low confidence

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

14–38 · low confidence

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

14–38 · low confidence

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

13–35 · low confidence

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

13–35 · low confidence

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

13–35 · low confidence

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

13–35 · low confidence

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

13–35 · low confidence

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

12–32 · low confidence

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

12–32 · low confidence

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

12–32 · low confidence

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

12–32 · low confidence

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

12–31 · low confidence

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

11–31 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · low confidence

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

11–29 · 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 M365X 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
72 GB/s
Memory type
GDDR5
Memory bus width
128 bit
Memory clock
1.13 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
Tropo
Architecture
GCN 1.0
Generation
Gem System(R9 M300)
Foundry
TSMC
Process size
28 nm
Transistors
1.5 billion
Transistor density
12,200 K/mm²
Die size
123 mm²
Package
FCBGA-962
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
900 MHz
Boost clock
925 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
640
Texture mapping units
40
Render output units
16
L1 cache
16 KB
L2 cache
0.25 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)
1.2 TFLOPS
Double precision (FP64)
74 GFLOPS
Pixel rate
15 GPixel/s
Texture rate
37 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.

Bus interface
PCIe 3.0 x16

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
11.1
OpenGL
4.6
Vulkan
1.2
OpenCL
1.2
Shader model
5.1

Listings

Where to buy a Radeon R9 M365X

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

72 GB/s

Largest model

DeciLM 6B

At 4 GB of GDDR5 the Radeon R9 M365X 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 72 GB/s across a 128-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 1.13 GHz. Both halves matter, and neither is visible in a gaming benchmark.

In practice that combination tops out at DeciLM 6B — 5.7B, compressed to Q3_K_M, generating around 11.3 tokens per second.

The chip and how it was built

The Radeon R9 M365X is built on the Tropo graphics processor, using AMD's GCN 1.0 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 123 mm², holding 1.5 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

FP64

74 GFLOPS

Double-precision throughput is 74 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 900 MHz at base to 925 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 M365X has 16 KB of L1 cache, backed by 0.25 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 640 shading units, 40 texture mapping units, and 16 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

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 Radeon R9 M365X

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 10.6 tok/s
  2. 02 Voxtral Mini 4.7B · Q4_K_M · Jul 2025 11.7 tok/s
  3. 03 Typhoon 2.1 Gemma 4B 4B · Q4_K_M · May 2025 13.7 tok/s
  4. 04 Qwen3-4B 4B · Q3_K_M · Apr 2025 16.1 tok/s
  5. 05 Gemma 3 QAT 4B 4B · Q4_K_M · Apr 2025 13.7 tok/s
  6. 06 Gemma 3 4B 4B · Q4_K_M · Mar 2025 13.7 tok/s
  7. 07 Phi-4-Multimodal 5.6B · Q3_K_M · Mar 2025 11.5 tok/s
  8. 08 Minitron 4B 4.2B · Q4_K_M · Nov 2024 13.1 tok/s
  9. 09 XVERSE-MoE-A4.2B 4.2B · Q4_K_M · Apr 2024 13.1 tok/s
  10. 10 DeciLM 6B 5.7B · Q3_K_M · Sep 2023 11.3 tok/s

The fastest AI models on a Radeon R9 M365X

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 23.8 tok/s
  2. 02 Gemma 3 1B 1B · Q8_0 · 1.8 GB 23.8 tok/s
  3. 03 LLama 3..2 Typhoon 2 1B 1B · Q8_0 · 1.8 GB 23.8 tok/s
  4. 04 OLMo-1B 1B · Q8_0 · 1.8 GB 23.8 tok/s
  5. 05 HGRN 1B (WT 103) 1B · Q8_0 · 1.8 GB 23.8 tok/s
  6. 06 Pythia-1b 1B · Q8_0 · 1.8 GB 23.8 tok/s
  7. 07 OpenELM-1.1B 1.1B · Q8_0 · 1.9 GB 22.0 tok/s
  8. 08 TinyLlama-1.1B (1T token checkpoint) 1.1B · Q8_0 · 1.9 GB 21.6 tok/s
  9. 09 TinyLlama-1.1B (3T token checkpoint) 1.1B · Q8_0 · 1.9 GB 21.6 tok/s
  10. 10 DeciCoder-1B 1.1B · Q8_0 · 1.9 GB 21.6 tok/s

Step by step

How to work out the tokens per second of a Radeon R9 M365X

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

    Every one of the 97 models this Radeon R9 M365X runs is in the table above. Search narrows it by name or by size.

  2. 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 4 GB it is often what pushes a large model over the edge.

  3. 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.

  4. 04

    Read the speed and the range

    The figures are calculated, not measured. 23.8 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

    Check the memory column before committing

    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

    Open the model to compare cards

    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 M365X is the right buy for it or merely a card that fits.

Answers

Radeon R9 M365X — common questions

01

Is the Radeon R9 M365X 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.

02

Can a Radeon R9 M365X run a model that does not fit in its memory?

Offloading past the card's 4 GB is possible and usually a false economy: the system-memory portion is slow enough to dominate the result.

03

Would two Radeon R9 M365X cards be twice as fast?

No. A second Radeon R9 M365X doubles the memory to 8 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.

04

What AI models can a Radeon R9 M365X run?

97 of the 679 open-weight language models we track fit on a Radeon R9 M365X 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.

05

What is the largest AI model a Radeon R9 M365X can run?

The largest model in our catalogue that fits on a Radeon R9 M365X is DeciLM 6B at 5.7B parameters, compressed to Q3_K_M. It generates roughly 11.3 tokens per second and needs about 3.5 GB of the card's memory.

06

How many tokens per second does a Radeon R9 M365X produce?

It depends on the model. On a Radeon R9 M365X the fastest model we track is Gemma 3 QAT 1B at about 23.8 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.

07

How much memory does a Radeon R9 M365X have?

A Radeon R9 M365X 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.

08

What is the memory bandwidth of a Radeon R9 M365X?

The Radeon R9 M365X has 72 GB/s of memory bandwidth, across a 128-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.

09

What type of memory does a Radeon R9 M365X use?

It uses GDDR5 clocked at 1.13 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.

10

Who makes the Radeon R9 M365X?

The Radeon R9 M365X is a AMD product, with the chip manufactured by TSMC, on a 28 nm process.

11

When was the Radeon R9 M365X released?

The Radeon R9 M365X was released in May 2015.

12

How much cache does a Radeon R9 M365X have?

The Radeon R9 M365X has 16 KB of L1 cache, and 0.25 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.

13

Does the Radeon R9 M365X support CUDA?

No. CUDA is NVIDIA-only, and the Radeon R9 M365X 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.

14

What bus interface does the Radeon R9 M365X 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.

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