Leaderboard Β· All comparisons Β· LynxBenchAI 26Q3 Index

NVIDIA B300 SXM6 AC vs AMD Instinct MI350X for AI

Device pages: NVIDIA B300 SXM6 AC Β· AMD Instinct MI350X

On the LynxBenchAI 26Q3 Index, the NVIDIA B300 SXM6 AC scores 1.10x the AMD Instinct MI350X overall (Training 1.32x, Inference 0.97x, Compute 1.01x). It leads on Training and Compute and trails on Inference.

Scores on the LynxBenchAI 26Q3 Index

Ratio = the B300 SXM6 AC's score divided by the AMD MI350X's
ScoreRatioB300 SXM6 ACAMD MI350X
Overall (GT)1.10x1277.421156.14
Training1.32x1080.48817.03
Inference0.97x2105.932166.65
Compute1.01x624.58617.19

When to Choose Which

  • Choose the B300 SXM6 AC for training (1.32x the AMD MI350X).
  • Level on inference: the two are within 10% (0.97x).
  • Level on raw compute: the two are within 10% (1.01x).

From the LynxBenchAI 26Q3 Index category scores, which are not raw throughput; a lead under 10% counts as level.

Per Model and Precision

LynxBenchAI score per model and precision; ratio = B300 SXM6 AC / AMD MI350X
ModelPrecisionRatioB300 SXM6 ACAMD MI350X
compute
Dense MatMulBF161.31x2853.412174.56
Dense MatMulFP161.38x2681.771944.54
Dense MatMulFP321.38x2121.521534.96
Dense MatMulFP640.06x6.97122.13
Sparse MatMulFP320.95x186.46195.34
Sparse MatMulFP640.47x131.34280.12
inference
DistilBERTFP160.85x4366.175109.02
DistilBERTFP80.73x1863.412541.77
DistilBERTINT80.34x733.722156.42
DistilGPT2FP160.35x1900.435445.98
DistilGPT2FP80.32x906.522833.38
DistilGPT2INT80.23x563.792428.68
Flan-T5 SmallFP161.26x6991.615565.58
Flan-T5 SmallFP80.84x2362.982820.77
Flan-T5 SmallINT80.35x826.522341.95
GraphGPS (Peptides)FP161.62x2274.511405.97
GraphGPS (Peptides)FP81.38x1157.93837.37
GraphGPS (Peptides)INT81.01x793.56789.04
MobileNetV3FP163.36x4720.151404.76
MobileNetV3INT82.51x1605.82638.72
training
DistilBERTBF161.14x2127.791859.31
DistilBERTFP321.16x2448.422113.86
DistilGPT2BF160.50x703.681394.94
DistilGPT2FP321.04x1928.261860.31
Flan-T5 SmallBF160.92x1099.161200.09
Flan-T5 SmallFP321.12x2203.371967.35
GraphGPS (Peptides)BF161.53x575.06376.34
GraphGPS (Peptides)FP321.26x612.45486.15
MobileNetV3BF162.42x253.32104.50
MobileNetV3FP328.02x642.8480.12

Related Comparisons

Each figure is the first device's overall score divided by the second's.

Measure your own machine: pip install lynxbench-ai Β· Install guide β†’

How to Read These Results

A LynxBenchAI score is sustained throughput on a fixed catalogue of PyTorch models, measured after a warm-up at a batch size raised until throughput stops improving, so it is what the machine holds under load, not its best instant. Training, Inference and Compute are three separate scores; GT combines them (Training and Inference weigh 0.4 each, Compute 0.2).

Every run uses the stock, publicly released PyTorch stack, so a result is broadly indicative of the out-of-the-box PyTorch experience on that hardware, and so of custom PyTorch models too. It does not run your own model, and it is not a vendor-tuned peak like an MLPerf submission.

Scores compare only within one Index: the 26Q3 Index fixes the models, precisions, correctness thresholds and scoring, and a later Index may change them. Each test is one timed window, the scores have no 0-100 scale, and a precision a device cannot run scores zero rather than being skipped.

LynxBenchAI is built by TechnoLynx, which the European Commission engaged as an independent expert advisor on AI performance and benchmarking for AI Gigafactories under the EuroHPC Joint Undertaking (case study).

Questions

Is the NVIDIA B300 SXM6 AC faster than the AMD Instinct MI350X for AI?
On the LynxBenchAI 26Q3 Index, the NVIDIA B300 SXM6 AC scores 1.10x the AMD Instinct MI350X overall (Training 1.32x, Inference 0.97x, Compute 1.01x). It leads on Training and Compute and trails on Inference.
Should I choose the NVIDIA B300 SXM6 AC or the AMD Instinct MI350X?
Choose the B300 SXM6 AC for training (1.32x the AMD MI350X). Level on inference: the two are within 10% (0.97x). Level on raw compute: the two are within 10% (1.01x). These follow the LynxBenchAI 26Q3 Index category scores, which are not raw throughput.
Where is the difference between the NVIDIA B300 SXM6 AC and the AMD Instinct MI350X largest?
On the LynxBenchAI 26Q3 Index, the ratio is highest on MobileNetV3 at FP32 (Training), where the NVIDIA B300 SXM6 AC scores 8.02x the AMD Instinct MI350X, and lowest on Dense MatMul at FP64 (Compute), at 0.06x.
What does this result tell me about my own PyTorch model?
Every run uses the stock, publicly released PyTorch stack, so a result is broadly indicative of the out-of-the-box PyTorch experience on that hardware, and so of custom PyTorch models too. It does not run your own model, and it is not a vendor-tuned peak like an MLPerf submission.

The Personal Edition submits your benchmark results to TechnoLynx's servers as part of participating in the public leaderboard. If that isn't acceptable for your use case, contact TechnoLynx about Press, Pro, or Enterprise licenses.

Get Started