Ollama benchmark Q2 2024 - Exoscale A40 - Consumption

Go back to list

As power consumption is one of the main aspect of performance, we obtained several measurements of usage through the gpu-burn software:

  • GFLOPS: As therorical raw performance value
  • Temperature: Average hotness during the operation
  • Watt: Average energy delivery

 

{ "configuration": { "chart": { "type": "spline", "polar": false, "zoomType": "", "options3d": {}, "height": null, "width": null, "margin": null, "inverted": false, "zooming": {} }, "credits": { "enabled": false }, "title": { "text": "" }, "colorAxis": null, "subtitle": { "text": "" }, "xAxis": { "title": { "text": [ "Memory usage" ], "useHTML": false, "style": { "color": "#666666" } }, "categories": [ 10, 20, 30, 40, 50, 60, 70, 80, 90 ], "lineWidth": 1, "tickInterval": null, "tickWidth": 1, "tickLength": 10, "tickPixelInterval": null, "plotLines": null, "labels": { "format": "{value}%" }, "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, "crosshair": true }, "yAxis": [ { "title": { "text": "Power usage", "style": { "color": "#3c8c40" } }, "categories": [], "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": 100, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": 0, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "format": "{value} W", "style": { "color": "#3c8c40" } } }, { "title": { "text": "Temperature", "style": { "color": "#3c0c40" } }, "categories": [], "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": 100, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 1, "gridLineColor": "#CCC", "min": 0, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "format": "{value} C\u00b0", "style": { "color": "#3c0c40" } }, "opposite": true }, { "title": { "text": "GFLOPS", "style": { "color": "#Ac8c40" } }, "categories": [], "plotLines": null, "plotBands": null, "lineWidth": null, "tickInterval": 100, "tickLength": 10, "floor": null, "ceiling": null, "gridLineInterpolation": null, "gridLineWidth": 0, "gridLineColor": "#CCC", "min": 0, "max": null, "minorTickInterval": null, "minorTickWidth": 0, "minTickInterval": null, "startOnTick": true, "endOnTick": null, "minRange": null, "type": "linear", "tickmarkPlacement": null, "labels": { "format": "{value}", "style": { "color": "#Ac8c40" } } } ], "zAxis": { "title": { "text": "" } }, "plotOptions": { "series": { "dataLabels": { "enabled": false, "format": null, "distance": 30, "align": "center", "inside": null, "allowOverlap": false, "style": { "fontSize": "11px" } }, "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": "Power usage", "yAxis": 0, "color": "#3c8c40", "data": [ 142.17857142857142, 220.55357142857142, 220.58928571428572, 207.25, 219.82142857142856, 217.02604166666666, 230.27777777777777, 237.66666666666669, 243.28095238095239 ], "lineWidth": 5, "tooltip": { "valueSuffix": " W" } }, { "name": "Temperature", "yAxis": 1, "color": "#3c0c40", "data": [ 57.37662337662337, 61.05194805194805, 63.467532467532465, 67.27272727272727, 70.24675324675326, 71.39448051948052, 72.64583333333333, 73.4040404040404, 74.2611111111111 ], "lineWidth": 5, "tooltip": { "valueSuffix": " C\u00b0" } }, { "name": "GFLOPS", "yAxis": 2, "color": "#Ac8c40", "data": [ 21891.103896103894, 22301.896103896106, 22053.87012987013, 22200.080808080806, 22253.376623376622, 22008.22023809524, 22111.34375, 22015.242424242428, 22112.409523809525 ], "lineWidth": 5, "tooltip": { "valueSuffix": " GFLOPS" } } ], "drilldown": {}, "tooltip": { "enabled": true, "useHTML": false, "format": null, "headerFormat": "", "pointFormat": "<span style=\"color:{series.color}\">{series.name}</span>: <b>{point.y:.2f}</b><br/>", "footerFormat": "", "shared": true, "outside": false, "valueDecimals": null, "split": false }, "annotations": null }, "hc_type": "chart", "id": "164905821353094611133654911443005109853" }

Notes

  • Please keep in mind that GFLOPS doesn't directly reflect what LLM can directly provides
  • Power consumption is not in the original sofware. Cloud Mercato did a pull request to include this value in results. Feel free to help us to push this contribution
  • An NVIDIA A40 has idle temperature of 33 C° and 14 Watts
  • No errors were produced by GPU computations during our tests