OVHcloud GPU benchmark - Whisper FP32

Go back to list

Whipser allows to perform recognition with FP16 and FP32 precisions. In this panel we ran the same testing changing only the data type:

# sample=en-male-1  # or en-male-2, en-male-3, en-female-1, en-female-2, en-female-3
# model_name=tiny # or base, small, medium, large
whisper-benchmark $sample  --model-name $model_name  --device cuda
 
 

 

 

{ "configuration": { "chart": { "type": "bar", "polar": false, "zoomType": "", "options3d": {}, "height": 550, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "Tiny" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ "provider__short_name", "flavor__name", "flavor__gpu_model" ], "lineWidth": 1, "tickInterval": null, "tickWidth": 0, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "enabled": false, "format": null, "formatter": "", "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false, "step": 0 }, "plotBands": null, "visible": true, "floor": null, "ceiling": null, "type": "linear", "min": null, "gridLineWidth": null, "gridLineColor": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "tickmarkPlacement": null, "units": null, "minRange": null }, "yAxis": { "title": { "text": [ "Frame/second<br>Higher is better" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false } }, "zAxis": { "title": { "text": "Frame/second<br>Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "allowOverlap": false, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false, "findNearestPointBy": "x" } }, "navigator": { "enabled": false }, "scrollbar": { "enabled": false }, "rangeSelector": { "enabled": false, "inputEnabled": false }, "legend": { "enabled": true, "maxHeight": null, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS g5.xlarge NVIDIA A10G", "data": [ [ 0, 2946.9300948754885 ] ], "grouping": false, "color": "#f7981d" }, { "name": "AWS p3.2xlarge Tesla V100-SXM2-16GB", "data": [ [ 1, 1813.6143496062848 ] ], "grouping": false, "color": "#f7981d" }, { "name": "Azure Standard_NC40ads_H100_v5 NVIDIA H100 NVL", "data": [ [ 2, 5085.84104127093 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NC6s_v3 Tesla V100-PCIE-16GB", "data": [ [ 3, 1995.4621091052968 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NV36ads_A10_v5 NVIDIA A10", "data": [ [ 4, 3563.043043626607 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Google a2-highgpu-1g NVIDIA A100-SXM4-40GB", "data": [ [ 5, 2412.2926284388554 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google a2-ultragpu-1g NVIDIA A100-SXM4-80GB", "data": [ [ 6, 2463.801274971783 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google g2-standard-16 NVIDIA L4", "data": [ [ 7, 2417.367534940729 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google n1-highmem-8 Intel Skylake Tesla V100 Tesla V100-SXM2-16GB", "data": [ [ 8, 2575.4389478553458 ] ], "grouping": false, "color": "#55b400" }, { "name": "OVH H100-380 NVIDIA H100 PCIe", "data": [ [ 9, 4470.07164960548 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L4-90 NVIDIA L4", "data": [ [ 10, 4777.157698381378 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L40S-90 NVIDIA L40S", "data": [ [ 11, 4785.6197872677885 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH T1-LE-45 Tesla V100-PCIE-16GB", "data": [ [ 12, 2390.699327779465 ] ], "grouping": false, "color": "#484848" } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.1f} frame/sec</b>", "footerFormat": "", "shared": false, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "tiny" }
{ "configuration": { "chart": { "type": "bar", "polar": false, "zoomType": "", "options3d": {}, "height": 550, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "Base" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ "provider__short_name", "flavor__name", "flavor__gpu_model" ], "lineWidth": 1, "tickInterval": null, "tickWidth": 0, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "enabled": false, "format": null, "formatter": "", "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false, "step": 0 }, "plotBands": null, "visible": true, "floor": null, "ceiling": null, "type": "linear", "min": null, "gridLineWidth": null, "gridLineColor": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "tickmarkPlacement": null, "units": null, "minRange": null }, "yAxis": { "title": { "text": [ "Frame/second<br>Higher is better" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false } }, "zAxis": { "title": { "text": "Frame/second<br>Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "allowOverlap": false, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false, "findNearestPointBy": "x" } }, "navigator": { "enabled": false }, "scrollbar": { "enabled": false }, "rangeSelector": { "enabled": false, "inputEnabled": false }, "legend": { "enabled": true, "maxHeight": null, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS g5.xlarge NVIDIA A10G", "data": [ [ 0, 2509.666785576343 ] ], "grouping": false, "color": "#f7981d" }, { "name": "AWS p3.2xlarge Tesla V100-SXM2-16GB", "data": [ [ 1, 1469.840315961509 ] ], "grouping": false, "color": "#f7981d" }, { "name": "Azure Standard_NC40ads_H100_v5 NVIDIA H100 NVL", "data": [ [ 2, 4266.499543681948 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NC6s_v3 Tesla V100-PCIE-16GB", "data": [ [ 3, 1672.0706258158796 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NV36ads_A10_v5 NVIDIA A10", "data": [ [ 4, 3051.9249656445427 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Google a2-highgpu-1g NVIDIA A100-SXM4-40GB", "data": [ [ 5, 2048.220512952112 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google a2-ultragpu-1g NVIDIA A100-SXM4-80GB", "data": [ [ 6, 2059.064037267334 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google g2-standard-16 NVIDIA L4", "data": [ [ 7, 2015.6690645340398 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google n1-highmem-8 Intel Skylake Tesla V100 Tesla V100-SXM2-16GB", "data": [ [ 8, 2190.590942725262 ] ], "grouping": false, "color": "#55b400" }, { "name": "OVH H100-380 NVIDIA H100 PCIe", "data": [ [ 9, 3903.336687534013 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L4-90 NVIDIA L4", "data": [ [ 10, 4034.6864316269553 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L40S-90 NVIDIA L40S", "data": [ [ 11, 4133.632428246811 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH T1-LE-45 Tesla V100-PCIE-16GB", "data": [ [ 12, 2048.1961895744025 ] ], "grouping": false, "color": "#484848" } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.1f} frame/sec</b>", "footerFormat": "", "shared": false, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "base" }
{ "configuration": { "chart": { "type": "bar", "polar": false, "zoomType": "", "options3d": {}, "height": 550, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "Small" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ "provider__short_name", "flavor__name", "flavor__gpu_model" ], "lineWidth": 1, "tickInterval": null, "tickWidth": 0, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "enabled": false, "format": null, "formatter": "", "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false, "step": 0 }, "plotBands": null, "visible": true, "floor": null, "ceiling": null, "type": "linear", "min": null, "gridLineWidth": null, "gridLineColor": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "tickmarkPlacement": null, "units": null, "minRange": null }, "yAxis": { "title": { "text": [ "Frame/second<br>Higher is better" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false } }, "zAxis": { "title": { "text": "Frame/second<br>Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "allowOverlap": false, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false, "findNearestPointBy": "x" } }, "navigator": { "enabled": false }, "scrollbar": { "enabled": false }, "rangeSelector": { "enabled": false, "inputEnabled": false }, "legend": { "enabled": true, "maxHeight": null, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS g5.xlarge NVIDIA A10G", "data": [ [ 0, 1675.7377994297842 ] ], "grouping": false, "color": "#f7981d" }, { "name": "AWS p3.2xlarge Tesla V100-SXM2-16GB", "data": [ [ 1, 1009.5867561007136 ] ], "grouping": false, "color": "#f7981d" }, { "name": "Azure Standard_NC40ads_H100_v5 NVIDIA H100 NVL", "data": [ [ 2, 3001.637979445983 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NC6s_v3 Tesla V100-PCIE-16GB", "data": [ [ 3, 1081.8473539310571 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NV36ads_A10_v5 NVIDIA A10", "data": [ [ 4, 2012.2837623727846 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Google a2-highgpu-1g NVIDIA A100-SXM4-40GB", "data": [ [ 5, 1364.0845162810785 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google a2-ultragpu-1g NVIDIA A100-SXM4-80GB", "data": [ [ 6, 1375.7784044391221 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google g2-standard-16 NVIDIA L4", "data": [ [ 7, 1315.3686353467167 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google n1-highmem-8 Intel Skylake Tesla V100 Tesla V100-SXM2-16GB", "data": [ [ 8, 1500.5446223097194 ] ], "grouping": false, "color": "#55b400" }, { "name": "OVH H100-380 NVIDIA H100 PCIe", "data": [ [ 9, 3032.6845834486103 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L4-90 NVIDIA L4", "data": [ [ 10, 2520.976939993426 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L40S-90 NVIDIA L40S", "data": [ [ 11, 2803.71980716785 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH T1-LE-45 Tesla V100-PCIE-16GB", "data": [ [ 12, 1352.9154569064672 ] ], "grouping": false, "color": "#484848" } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.1f} frame/sec</b>", "footerFormat": "", "shared": false, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "small" }
{ "configuration": { "chart": { "type": "bar", "polar": false, "zoomType": "", "options3d": {}, "height": 550, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "Medium" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ "provider__short_name", "flavor__name", "flavor__gpu_model" ], "lineWidth": 1, "tickInterval": null, "tickWidth": 0, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "enabled": false, "format": null, "formatter": "", "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false, "step": 0 }, "plotBands": null, "visible": true, "floor": null, "ceiling": null, "type": "linear", "min": null, "gridLineWidth": null, "gridLineColor": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "tickmarkPlacement": null, "units": null, "minRange": null }, "yAxis": { "title": { "text": [ "Frame/second<br>Higher is better" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false } }, "zAxis": { "title": { "text": "Frame/second<br>Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "allowOverlap": false, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false, "findNearestPointBy": "x" } }, "navigator": { "enabled": false }, "scrollbar": { "enabled": false }, "rangeSelector": { "enabled": false, "inputEnabled": false }, "legend": { "enabled": true, "maxHeight": null, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS g5.xlarge NVIDIA A10G", "data": [ [ 0, 984.1330180744648 ] ], "grouping": false, "color": "#f7981d" }, { "name": "AWS p3.2xlarge Tesla V100-SXM2-16GB", "data": [ [ 1, 575.366327067824 ] ], "grouping": false, "color": "#f7981d" }, { "name": "Azure Standard_NC40ads_H100_v5 NVIDIA H100 NVL", "data": [ [ 2, 1857.1838093185704 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NC6s_v3 Tesla V100-PCIE-16GB", "data": [ [ 3, 643.884008322358 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NV36ads_A10_v5 NVIDIA A10", "data": [ [ 4, 1122.1485767223212 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Google a2-highgpu-1g NVIDIA A100-SXM4-40GB", "data": [ [ 5, 801.1369490819542 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google a2-ultragpu-1g NVIDIA A100-SXM4-80GB", "data": [ [ 6, 807.1577742336061 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google g2-standard-16 NVIDIA L4", "data": [ [ 7, 749.926404692831 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google n1-highmem-8 Intel Skylake Tesla V100 Tesla V100-SXM2-16GB", "data": [ [ 8, 884.1375873957717 ] ], "grouping": false, "color": "#55b400" }, { "name": "OVH H100-380 NVIDIA H100 PCIe", "data": [ [ 9, 1841.5219590702534 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L4-90 NVIDIA L4", "data": [ [ 10, 1096.3410311829418 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L40S-90 NVIDIA L40S", "data": [ [ 11, 1716.4475442032353 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH T1-LE-45 Tesla V100-PCIE-16GB", "data": [ [ 12, 809.1519261103973 ] ], "grouping": false, "color": "#484848" } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.1f} frame/sec</b>", "footerFormat": "", "shared": false, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "medium" }
{ "configuration": { "chart": { "type": "bar", "polar": false, "zoomType": "", "options3d": {}, "height": 550, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "Large" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ "provider__short_name", "flavor__name", "flavor__gpu_model" ], "lineWidth": 1, "tickInterval": null, "tickWidth": 0, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "enabled": false, "format": null, "formatter": "", "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false, "step": 0 }, "plotBands": null, "visible": true, "floor": null, "ceiling": null, "type": "linear", "min": null, "gridLineWidth": null, "gridLineColor": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "tickmarkPlacement": null, "units": null, "minRange": null }, "yAxis": { "title": { "text": [ "Frame/second<br>Higher is better" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": null, "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": null, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": null, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "enabled": true, "formatter": null, "style": { "color": "#666666", "cursor": "default", "fontSize": "11px" }, "useHTML": false } }, "zAxis": { "title": { "text": "Frame/second<br>Higher is better" } }, "plotOptions": { "series": { "dataLabels": { "enabled": true, "format": "{series.name}", "distance": 30, "align": "left", "inside": true, "allowOverlap": false, "style": { "fontSize": "17px" } }, "showInLegend": null, "turboThreshold": 1000, "stacking": "", "groupPadding": 0, "centerInCategory": false, "findNearestPointBy": "x" } }, "navigator": { "enabled": false }, "scrollbar": { "enabled": false }, "rangeSelector": { "enabled": false, "inputEnabled": false }, "legend": { "enabled": true, "maxHeight": null, "align": "center", "verticalAlign": "bottom", "layout": "horizontal", "width": null, "margin": 12, "reversed": false }, "series": [ { "name": "AWS g5.xlarge NVIDIA A10G", "data": [ [ 0, 713.0774584421916 ] ], "grouping": false, "color": "#f7981d" }, { "name": "AWS p3.2xlarge Tesla V100-SXM2-16GB", "data": [ [ 1, 424.27827198225947 ] ], "grouping": false, "color": "#f7981d" }, { "name": "Azure Standard_NC40ads_H100_v5 NVIDIA H100 NVL", "data": [ [ 2, 1390.8646164598201 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NC6s_v3 Tesla V100-PCIE-16GB", "data": [ [ 3, 489.5767323850335 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Azure Standard_NV36ads_A10_v5 NVIDIA A10", "data": [ [ 4, 673.9991928503338 ] ], "grouping": false, "color": "#55b3ff" }, { "name": "Google a2-highgpu-1g NVIDIA A100-SXM4-40GB", "data": [ [ 5, 601.5859389708068 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google a2-ultragpu-1g NVIDIA A100-SXM4-80GB", "data": [ [ 6, 606.9649252978043 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google g2-standard-16 NVIDIA L4", "data": [ [ 7, 533.3011270804348 ] ], "grouping": false, "color": "#55b400" }, { "name": "Google n1-highmem-8 Intel Skylake Tesla V100 Tesla V100-SXM2-16GB", "data": [ [ 8, 657.4965994753069 ] ], "grouping": false, "color": "#55b400" }, { "name": "OVH H100-380 NVIDIA H100 PCIe", "data": [ [ 9, 1363.462759224739 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L4-90 NVIDIA L4", "data": [ [ 10, 603.0972969339092 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH L40S-90 NVIDIA L40S", "data": [ [ 11, 1233.1721862403263 ] ], "grouping": false, "color": "#484848" }, { "name": "OVH T1-LE-45 Tesla V100-PCIE-16GB", "data": [ [ 12, 612.3247665447378 ] ], "grouping": false, "color": "#484848" } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.1f} frame/sec</b>", "footerFormat": "", "shared": false, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "large" }

Cloud Mercato's observations:

  • All GPU perform better in FP32
  • The most latest GPUs, H100, L4, L40S, perform the better
  • L4 quickly loose speed after the base model
  • Starting at the medium model, only L40S and H100 still maintain a high level of performance
  • V100 performs as well as A100