chore: align naming for micro instance (#20656)
This commit is contained in:
Kevin Grüneberg
GitHub
@@ -34,18 +34,18 @@ This benchmark uses the dbpedia-entities-openai-1M dataset containing 1,000,000
|
||||
>
|
||||
<TabPanel id="gte384" label="gte-small-384">
|
||||
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ---------- | ------ |
|
||||
| Starter | 100,000 | 16 | 64 | 60 | 580 | 0.017 sec | 0.024 sec | 1.2 (Swap) | 1 GB |
|
||||
| Small | 250,000 | 24 | 64 | 60 | 440 | 0.022 sec | 0.033 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 24 | 64 | 80 | 350 | 0.028 sec | 0.045 sec | 4 GB | 4 GB |
|
||||
| Large | 1,000,000 | 32 | 80 | 100 | 270 | 0.073 sec | 0.108 sec | 7 GB | 8 GB |
|
||||
| XL | 1,000,000 | 32 | 80 | 100 | 525 | 0.038 sec | 0.059 sec | 9 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 32 | 80 | 100 | 790 | 0.025 sec | 0.037 sec | 9 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 32 | 80 | 100 | 1650 | 0.015 sec | 0.018 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 32 | 80 | 100 | 2690 | 0.015 sec | 0.016 sec | 13 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 32 | 80 | 100 | 3900 | 0.014 sec | 0.016 sec | 13 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 32 | 80 | 100 | 4200 | 0.014 sec | 0.016 sec | 20 GB | 256 GB |
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ---------- | ------ |
|
||||
| Micro | 100,000 | 16 | 64 | 60 | 580 | 0.017 sec | 0.024 sec | 1.2 (Swap) | 1 GB |
|
||||
| Small | 250,000 | 24 | 64 | 60 | 440 | 0.022 sec | 0.033 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 24 | 64 | 80 | 350 | 0.028 sec | 0.045 sec | 4 GB | 4 GB |
|
||||
| Large | 1,000,000 | 32 | 80 | 100 | 270 | 0.073 sec | 0.108 sec | 7 GB | 8 GB |
|
||||
| XL | 1,000,000 | 32 | 80 | 100 | 525 | 0.038 sec | 0.059 sec | 9 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 32 | 80 | 100 | 790 | 0.025 sec | 0.037 sec | 9 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 32 | 80 | 100 | 1650 | 0.015 sec | 0.018 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 32 | 80 | 100 | 2690 | 0.015 sec | 0.016 sec | 13 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 32 | 80 | 100 | 3900 | 0.014 sec | 0.016 sec | 13 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 32 | 80 | 100 | 4200 | 0.014 sec | 0.016 sec | 20 GB | 256 GB |
|
||||
|
||||
Accuracy was 0.99 for benchmarks.
|
||||
|
||||
@@ -65,18 +65,18 @@ This benchmark uses the [gist-960](http://corpus-texmex.irisa.fr/) dataset, whic
|
||||
>
|
||||
<TabPanel id="openai1536" label="OpenAI-1536">
|
||||
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 30,000 | 16 | 64 | 65 | 430 | 0.024 sec | 0.034 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 100,000 | 32 | 80 | 60 | 260 | 0.040 sec | 0.054 sec | 2.2 GB (Swap) | 2 GB |
|
||||
| Medium | 250,000 | 32 | 80 | 90 | 120 | 0.083 sec | 0.106 sec | 4 GB | 4 GB |
|
||||
| Large | 500,000 | 32 | 80 | 120 | 160 | 0.063 sec | 0.087 sec | 7 GB | 8 GB |
|
||||
| XL | 1,000,000 | 32 | 80 | 200 | 200 | 0.049 sec | 0.072 sec | 13 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 32 | 80 | 200 | 340 | 0.025 sec | 0.029 sec | 17 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 32 | 80 | 200 | 630 | 0.031 sec | 0.050 sec | 18 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 32 | 80 | 200 | 1100 | 0.034 sec | 0.048 sec | 19 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 32 | 80 | 200 | 1420 | 0.041 sec | 0.095 sec | 21 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 32 | 80 | 200 | 1650 | 0.037 sec | 0.081 sec | 23 GB | 256 GB |
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 30,000 | 16 | 64 | 65 | 430 | 0.024 sec | 0.034 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 100,000 | 32 | 80 | 60 | 260 | 0.040 sec | 0.054 sec | 2.2 GB (Swap) | 2 GB |
|
||||
| Medium | 250,000 | 32 | 80 | 90 | 120 | 0.083 sec | 0.106 sec | 4 GB | 4 GB |
|
||||
| Large | 500,000 | 32 | 80 | 120 | 160 | 0.063 sec | 0.087 sec | 7 GB | 8 GB |
|
||||
| XL | 1,000,000 | 32 | 80 | 200 | 200 | 0.049 sec | 0.072 sec | 13 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 32 | 80 | 200 | 340 | 0.025 sec | 0.029 sec | 17 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 32 | 80 | 200 | 630 | 0.031 sec | 0.050 sec | 18 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 32 | 80 | 200 | 1100 | 0.034 sec | 0.048 sec | 19 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 32 | 80 | 200 | 1420 | 0.041 sec | 0.095 sec | 21 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 32 | 80 | 200 | 1650 | 0.037 sec | 0.081 sec | 23 GB | 256 GB |
|
||||
|
||||
Accuracy was 0.99 for benchmarks.
|
||||
|
||||
@@ -98,18 +98,18 @@ This benchmark uses the [dbpedia-entities-openai-1M](https://huggingface.co/data
|
||||
>
|
||||
<TabPanel id="openai1536" label="OpenAI-1536">
|
||||
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 15,000 | 16 | 40 | 40 | 480 | 0.011 sec | 0.016 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 50,000 | 32 | 64 | 100 | 175 | 0.031 sec | 0.051 sec | 2.2 GB (Swap) | 2 GB |
|
||||
| Medium | 100,000 | 32 | 64 | 100 | 240 | 0.083 sec | 0.126 sec | 4 GB | 4 GB |
|
||||
| Large | 224,482 | 32 | 64 | 100 | 280 | 0.017 sec | 0.028 sec | 8 GB | 8 GB |
|
||||
| XL | 500,000 | 24 | 56 | 100 | 360 | 0.055 sec | 0.135 sec | 13 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 24 | 56 | 250 | 560 | 0.036 sec | 0.058 sec | 32 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 24 | 56 | 250 | 950 | 0.021 sec | 0.033 sec | 39 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 24 | 56 | 250 | 1650 | 0.016 sec | 0.023 sec | 40 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 24 | 56 | 250 | 1900 | 0.015 sec | 0.021 sec | 38 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 24 | 56 | 250 | 2200 | 0.015 sec | 0.020 sec | 40 GB | 256 GB |
|
||||
| Plan | Vectors | m | ef_construction | ef_search | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | --- | --------------- | --------- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 15,000 | 16 | 40 | 40 | 480 | 0.011 sec | 0.016 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 50,000 | 32 | 64 | 100 | 175 | 0.031 sec | 0.051 sec | 2.2 GB (Swap) | 2 GB |
|
||||
| Medium | 100,000 | 32 | 64 | 100 | 240 | 0.083 sec | 0.126 sec | 4 GB | 4 GB |
|
||||
| Large | 224,482 | 32 | 64 | 100 | 280 | 0.017 sec | 0.028 sec | 8 GB | 8 GB |
|
||||
| XL | 500,000 | 24 | 56 | 100 | 360 | 0.055 sec | 0.135 sec | 13 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 24 | 56 | 250 | 560 | 0.036 sec | 0.058 sec | 32 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 24 | 56 | 250 | 950 | 0.021 sec | 0.033 sec | 39 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 24 | 56 | 250 | 1650 | 0.016 sec | 0.023 sec | 40 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 24 | 56 | 250 | 1900 | 0.015 sec | 0.021 sec | 38 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 24 | 56 | 250 | 2200 | 0.015 sec | 0.020 sec | 40 GB | 256 GB |
|
||||
|
||||
Accuracy was 0.99 for benchmarks.
|
||||
|
||||
@@ -149,34 +149,34 @@ This benchmark uses the dbpedia-entities-openai-1M dataset containing 1,000,000
|
||||
>
|
||||
<TabPanel id="gte384_98" label="gte-small-384, accuracy=.98">
|
||||
|
||||
| Plan | Vectors | Lists | Probes | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | ----- | ------ | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 100,000 | 500 | 50 | 205 | 0.048 sec | 0.066 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 250,000 | 1000 | 60 | 160 | 0.062 sec | 0.079 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 2000 | 80 | 120 | 0.082 sec | 0.104 sec | 3.2 GB | 4 GB |
|
||||
| Large | 1,000,000 | 5000 | 150 | 75 | 0.269 sec | 0.375 sec | 6.5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 5000 | 150 | 150 | 0.131 sec | 0.178 sec | 9 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 5000 | 150 | 300 | 0.066 sec | 0.099 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 5000 | 150 | 570 | 0.035 sec | 0.046 sec | 10 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 5000 | 150 | 1400 | 0.023 sec | 0.028 sec | 12 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 5000 | 150 | 1550 | 0.030 sec | 0.039 sec | 12 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 5000 | 150 | 1800 | 0.030 sec | 0.039 sec | 16 GB | 256 GB |
|
||||
| Plan | Vectors | Lists | Probes | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | ----- | ------ | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 100,000 | 500 | 50 | 205 | 0.048 sec | 0.066 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 250,000 | 1000 | 60 | 160 | 0.062 sec | 0.079 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 2000 | 80 | 120 | 0.082 sec | 0.104 sec | 3.2 GB | 4 GB |
|
||||
| Large | 1,000,000 | 5000 | 150 | 75 | 0.269 sec | 0.375 sec | 6.5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 5000 | 150 | 150 | 0.131 sec | 0.178 sec | 9 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 5000 | 150 | 300 | 0.066 sec | 0.099 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 5000 | 150 | 570 | 0.035 sec | 0.046 sec | 10 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 5000 | 150 | 1400 | 0.023 sec | 0.028 sec | 12 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 5000 | 150 | 1550 | 0.030 sec | 0.039 sec | 12 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 5000 | 150 | 1800 | 0.030 sec | 0.039 sec | 16 GB | 256 GB |
|
||||
|
||||
</TabPanel>
|
||||
<TabPanel id="gte384_99" label="gte-small-384, accuracy=.99">
|
||||
|
||||
| Plan | Vectors | Lists | Probes | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | ----- | ------ | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 100,000 | 500 | 70 | 160 | 0.062 sec | 0.079 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 250,000 | 1000 | 100 | 100 | 0.096 sec | 0.113 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 2000 | 120 | 85 | 0.117 sec | 0.147 sec | 3.2 GB | 4 GB |
|
||||
| Large | 1,000,000 | 5000 | 250 | 50 | 0.394 sec | 0.521 sec | 6.5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 5000 | 250 | 100 | 0.197 sec | 0.255 sec | 10 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 5000 | 250 | 200 | 0.098 sec | 0.140 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 5000 | 250 | 390 | 0.051 sec | 0.066 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 5000 | 250 | 850 | 0.036 sec | 0.042 sec | 12 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 5000 | 250 | 1000 | 0.043 sec | 0.055 sec | 13 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 5000 | 250 | 1200 | 0.043 sec | 0.055 sec | 16 GB | 256 GB |
|
||||
| Plan | Vectors | Lists | Probes | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | ----- | ------ | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 100,000 | 500 | 70 | 160 | 0.062 sec | 0.079 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 250,000 | 1000 | 100 | 100 | 0.096 sec | 0.113 sec | 2 GB | 2 GB |
|
||||
| Medium | 500,000 | 2000 | 120 | 85 | 0.117 sec | 0.147 sec | 3.2 GB | 4 GB |
|
||||
| Large | 1,000,000 | 5000 | 250 | 50 | 0.394 sec | 0.521 sec | 6.5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 5000 | 250 | 100 | 0.197 sec | 0.255 sec | 10 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 5000 | 250 | 200 | 0.098 sec | 0.140 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 5000 | 250 | 390 | 0.051 sec | 0.066 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 5000 | 250 | 850 | 0.036 sec | 0.042 sec | 12 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 5000 | 250 | 1000 | 0.043 sec | 0.055 sec | 13 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 5000 | 250 | 1200 | 0.043 sec | 0.055 sec | 16 GB | 256 GB |
|
||||
|
||||
</TabPanel>
|
||||
</Tabs>
|
||||
@@ -194,18 +194,18 @@ This benchmark uses the [gist-960](http://corpus-texmex.irisa.fr/) dataset, whic
|
||||
>
|
||||
<TabPanel id="gist960" label="gist-960, probes = 10">
|
||||
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | ----- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 30,000 | 30 | 75 | 0.065 sec | 0.088 sec | 1.1 GB (Swap) | 1 GB |
|
||||
| Small | 100,000 | 100 | 78 | 0.064 sec | 0.092 sec | 1.8 GB | 2 GB |
|
||||
| Medium | 250,000 | 250 | 58 | 0.085 sec | 0.129 sec | 3.2 GB | 4 GB |
|
||||
| Large | 500,000 | 500 | 55 | 0.088 sec | 0.140 sec | 5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 1000 | 110 | 0.046 sec | 0.070 sec | 14 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 1000 | 235 | 0.083 sec | 0.136 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 1000 | 420 | 0.071 sec | 0.106 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 1000 | 815 | 0.072 sec | 0.106 sec | 13 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 1000 | 1150 | 0.052 sec | 0.078 sec | 15.5 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 1000 | 1345 | 0.072 sec | 0.106 sec | 17.5 GB | 256 GB |
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | ----- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 30,000 | 30 | 75 | 0.065 sec | 0.088 sec | 1.1 GB (Swap) | 1 GB |
|
||||
| Small | 100,000 | 100 | 78 | 0.064 sec | 0.092 sec | 1.8 GB | 2 GB |
|
||||
| Medium | 250,000 | 250 | 58 | 0.085 sec | 0.129 sec | 3.2 GB | 4 GB |
|
||||
| Large | 500,000 | 500 | 55 | 0.088 sec | 0.140 sec | 5 GB | 8 GB |
|
||||
| XL | 1,000,000 | 1000 | 110 | 0.046 sec | 0.070 sec | 14 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 1000 | 235 | 0.083 sec | 0.136 sec | 10 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 1000 | 420 | 0.071 sec | 0.106 sec | 11 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 1000 | 815 | 0.072 sec | 0.106 sec | 13 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 1000 | 1150 | 0.052 sec | 0.078 sec | 15.5 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 1000 | 1345 | 0.072 sec | 0.106 sec | 17.5 GB | 256 GB |
|
||||
|
||||
</TabPanel>
|
||||
</Tabs>
|
||||
@@ -223,36 +223,36 @@ This benchmark uses the [dbpedia-entities-openai-1M](https://huggingface.co/data
|
||||
>
|
||||
<TabPanel id="dbpedia1536" label="OpenAI-1536, probes = 10">
|
||||
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | ----- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Starter | 20,000 | 40 | 135 | 0.372 sec | 0.412 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 50,000 | 100 | 140 | 0.357 sec | 0.398 sec | 1.8 GB | 2 GB |
|
||||
| Medium | 100,000 | 200 | 130 | 0.383 sec | 0.446 sec | 3.7 GB | 4 GB |
|
||||
| Large | 250,000 | 500 | 130 | 0.378 sec | 0.434 sec | 7 GB | 8 GB |
|
||||
| XL | 500,000 | 1000 | 235 | 0.213 sec | 0.271 sec | 13.5 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 2000 | 380 | 0.133 sec | 0.236 sec | 30 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 2000 | 720 | 0.068 sec | 0.120 sec | 35 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 2000 | 1250 | 0.039 sec | 0.066 sec | 38 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 2000 | 1600 | 0.030 sec | 0.052 sec | 41 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 2000 | 1790 | 0.029 sec | 0.051 sec | 45 GB | 256 GB |
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | ----- | ---- | ------------ | ----------- | ------------- | ------ |
|
||||
| Micro | 20,000 | 40 | 135 | 0.372 sec | 0.412 sec | 1.2 GB (Swap) | 1 GB |
|
||||
| Small | 50,000 | 100 | 140 | 0.357 sec | 0.398 sec | 1.8 GB | 2 GB |
|
||||
| Medium | 100,000 | 200 | 130 | 0.383 sec | 0.446 sec | 3.7 GB | 4 GB |
|
||||
| Large | 250,000 | 500 | 130 | 0.378 sec | 0.434 sec | 7 GB | 8 GB |
|
||||
| XL | 500,000 | 1000 | 235 | 0.213 sec | 0.271 sec | 13.5 GB | 16 GB |
|
||||
| 2XL | 1,000,000 | 2000 | 380 | 0.133 sec | 0.236 sec | 30 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 2000 | 720 | 0.068 sec | 0.120 sec | 35 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 2000 | 1250 | 0.039 sec | 0.066 sec | 38 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 2000 | 1600 | 0.030 sec | 0.052 sec | 41 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 2000 | 1790 | 0.029 sec | 0.051 sec | 45 GB | 256 GB |
|
||||
|
||||
For 1,000,000 vectors 10 probes results to accuracy of 0.91. And for 500,000 vectors and below 10 probes results to accuracy in the range of 0.95 - 0.99. To increase accuracy, you need to increase the number of probes.
|
||||
|
||||
</TabPanel>
|
||||
<TabPanel id="dbpedia1536_40" label="OpenAI-1536, probes = 40">
|
||||
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------- | --------- | ----- | --- | ------------ | ----------- | --------- | ------ |
|
||||
| Starter | 20,000 | 40 | - | - | - | - | 1 GB |
|
||||
| Small | 50,000 | 100 | - | - | - | - | 2 GB |
|
||||
| Medium | 100,000 | 200 | - | - | - | - | 4 GB |
|
||||
| Large | 250,000 | 500 | - | - | - | - | 8 GB |
|
||||
| XL | 500,000 | 1000 | - | - | - | - | 16 GB |
|
||||
| 2XL | 1,000,000 | 2000 | 140 | 0.358 sec | 0.575 sec | 30 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 2000 | 270 | 0.186 sec | 0.304 sec | 35 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 2000 | 470 | 0.104 sec | 0.166 sec | 38 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 2000 | 600 | 0.085 sec | 0.132 sec | 41 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 2000 | 670 | 0.081 sec | 0.129 sec | 45 GB | 256 GB |
|
||||
| Plan | Vectors | Lists | QPS | Latency Mean | Latency p95 | RAM Usage | RAM |
|
||||
| ------ | --------- | ----- | --- | ------------ | ----------- | --------- | ------ |
|
||||
| Micro | 20,000 | 40 | - | - | - | - | 1 GB |
|
||||
| Small | 50,000 | 100 | - | - | - | - | 2 GB |
|
||||
| Medium | 100,000 | 200 | - | - | - | - | 4 GB |
|
||||
| Large | 250,000 | 500 | - | - | - | - | 8 GB |
|
||||
| XL | 500,000 | 1000 | - | - | - | - | 16 GB |
|
||||
| 2XL | 1,000,000 | 2000 | 140 | 0.358 sec | 0.575 sec | 30 GB | 32 GB |
|
||||
| 4XL | 1,000,000 | 2000 | 270 | 0.186 sec | 0.304 sec | 35 GB | 64 GB |
|
||||
| 8XL | 1,000,000 | 2000 | 470 | 0.104 sec | 0.166 sec | 38 GB | 128 GB |
|
||||
| 12XL | 1,000,000 | 2000 | 600 | 0.085 sec | 0.132 sec | 41 GB | 192 GB |
|
||||
| 16XL | 1,000,000 | 2000 | 670 | 0.081 sec | 0.129 sec | 45 GB | 256 GB |
|
||||
|
||||
For 1,000,000 vectors 40 probes results to accuracy of 0.98. Note that exact values may vary depending on the dataset and queries, we recommend to run benchmarks with your own data to get precise results. Use this table as a reference.
|
||||
|
||||
|
||||
@@ -8,18 +8,18 @@ export const meta = {
|
||||
|
||||
Every project on the Supabase Platform comes with its own dedicated Postgres instance running inside a virtual machine (VM). The following table describes the base instance with additional compute add-ons available if you need extra performance when scaling up Supabase.
|
||||
|
||||
| Plan | Hourly Price USD | Monthly Price USD | CPU | Memory | Connections: Direct | Connections: Pooler |
|
||||
| ------- | ---------------- | ----------------- | ----------------------- | ------ | ------------------- | ------------------- |
|
||||
| Starter | $0.01344 | ~$10 | 2-core ARM (shared) | 1 GB | 60 | 200 |
|
||||
| Small | $0.0206 | ~$15 | 2-core ARM (shared) | 2 GB | 90 | 200 |
|
||||
| Medium | $0.0822 | ~$60 | 2-core ARM (shared) | 4 GB | 120 | 200 |
|
||||
| Large | $0.1517 | ~$110 | 2-core ARM (dedicated) | 8 GB | 160 | 300 |
|
||||
| XL | $0.2877 | ~$210 | 4-core ARM (dedicated) | 16 GB | 240 | 700 |
|
||||
| 2XL | $0.562 | ~$410 | 8-core ARM (dedicated) | 32 GB | 380 | 1500 |
|
||||
| 4XL | $1.32 | ~$960 | 16-core ARM (dedicated) | 64 GB | 480 | 3000 |
|
||||
| 8XL | $2.562 | ~$1,870 | 32-core ARM (dedicated) | 128 GB | 490 | 6000 |
|
||||
| 12XL | $3.836 | ~$2,800 | 48-core ARM (dedicated) | 192 GB | 500 | 9000 |
|
||||
| 16XL | $5.12 | ~$3,730 | 64-core ARM (dedicated) | 256 GB | 500 | 12,000 |
|
||||
| Plan | Hourly Price USD | Monthly Price USD | CPU | Memory | Connections: Direct | Connections: Pooler |
|
||||
| ------ | ---------------- | ----------------- | ----------------------- | ------ | ------------------- | ------------------- |
|
||||
| Micro | $0.01344 | ~$10 | 2-core ARM (shared) | 1 GB | 60 | 200 |
|
||||
| Small | $0.0206 | ~$15 | 2-core ARM (shared) | 2 GB | 90 | 200 |
|
||||
| Medium | $0.0822 | ~$60 | 2-core ARM (shared) | 4 GB | 120 | 200 |
|
||||
| Large | $0.1517 | ~$110 | 2-core ARM (dedicated) | 8 GB | 160 | 300 |
|
||||
| XL | $0.2877 | ~$210 | 4-core ARM (dedicated) | 16 GB | 240 | 700 |
|
||||
| 2XL | $0.562 | ~$410 | 8-core ARM (dedicated) | 32 GB | 380 | 1500 |
|
||||
| 4XL | $1.32 | ~$960 | 16-core ARM (dedicated) | 64 GB | 480 | 3000 |
|
||||
| 8XL | $2.562 | ~$1,870 | 32-core ARM (dedicated) | 128 GB | 490 | 6000 |
|
||||
| 12XL | $3.836 | ~$2,800 | 48-core ARM (dedicated) | 192 GB | 500 | 9000 |
|
||||
| 16XL | $5.12 | ~$3,730 | 64-core ARM (dedicated) | 256 GB | 500 | 12,000 |
|
||||
|
||||
Number of connections above are recommended values.
|
||||
|
||||
@@ -39,18 +39,18 @@ When considering compute upgrades, assess whether your bottlenecks are hardware-
|
||||
|
||||
SSD Disks are attached to your servers and the disk performance depends on the compute add-on of your instance. Disk IO refers to two metrics: throughput (Megabits per Second) and IOPS (Input/Output Operations per Second).
|
||||
|
||||
| Plan | Max Disk Throughput | Baseline Disk Throughput | Max IOPS | Baseline IOPS |
|
||||
| ------- | ------------------- | ------------------------ | ----------- | ------------- |
|
||||
| Starter | 2,085 Mbps | 87 Mbps | 11,800 IOPS | 500 IOPS |
|
||||
| Small | 2,085 Mbps | 174 Mbps | 11,800 IOPS | 1,000 IOPS |
|
||||
| Medium | 2,085 Mbps | 347 Mbps | 11,800 IOPS | 2,000 IOPS |
|
||||
| Large | 4,750 Mbps | 630 Mbps | 20,000 IOPS | 3,600 IOPS |
|
||||
| XL | 4,750 Mbps | 1,188 Mbps | 20,000 IOPS | 6,000 IOPS |
|
||||
| 2XL | 4,750 Mbps | 2,375 Mbps | 20,000 IOPS | 12,000 IOPS |
|
||||
| 4XL | 4,750 Mbps | 4,750 Mbps | 20,000 IOPS | 20,000 IOPS |
|
||||
| 8XL | 9,500 Mbps | 9,500 Mbps | 40,000 IOPS | 40,000 IOPS |
|
||||
| 12XL | 14,250 Mbps | 14,250 Mbps | 50,000 IOPS | 50,000 IOPS |
|
||||
| 16XL | 19,000 Mbps | 19,000 Mbps | 80,000 IOPS | 80,000 IOPS |
|
||||
| Plan | Max Disk Throughput | Baseline Disk Throughput | Max IOPS | Baseline IOPS |
|
||||
| ------ | ------------------- | ------------------------ | ----------- | ------------- |
|
||||
| Micro | 2,085 Mbps | 87 Mbps | 11,800 IOPS | 500 IOPS |
|
||||
| Small | 2,085 Mbps | 174 Mbps | 11,800 IOPS | 1,000 IOPS |
|
||||
| Medium | 2,085 Mbps | 347 Mbps | 11,800 IOPS | 2,000 IOPS |
|
||||
| Large | 4,750 Mbps | 630 Mbps | 20,000 IOPS | 3,600 IOPS |
|
||||
| XL | 4,750 Mbps | 1,188 Mbps | 20,000 IOPS | 6,000 IOPS |
|
||||
| 2XL | 4,750 Mbps | 2,375 Mbps | 20,000 IOPS | 12,000 IOPS |
|
||||
| 4XL | 4,750 Mbps | 4,750 Mbps | 20,000 IOPS | 20,000 IOPS |
|
||||
| 8XL | 9,500 Mbps | 9,500 Mbps | 40,000 IOPS | 40,000 IOPS |
|
||||
| 12XL | 14,250 Mbps | 14,250 Mbps | 50,000 IOPS | 50,000 IOPS |
|
||||
| 16XL | 19,000 Mbps | 19,000 Mbps | 80,000 IOPS | 80,000 IOPS |
|
||||
|
||||
[Contact us](https://supabase.com/contact/enterprise) if you require a custom plan.
|
||||
|
||||
@@ -68,18 +68,18 @@ If you're unsure of how much throughput or IOPS your application requires, you c
|
||||
|
||||
The maximum number of replication slots and WAL senders depends on your compute add-on plan, as follows:
|
||||
|
||||
| Plan | Max Replication Slots | Max WAL Senders |
|
||||
| ------- | --------------------- | --------------- |
|
||||
| Starter | 5 | 5 |
|
||||
| Small | 5 | 5 |
|
||||
| Medium | 5 | 5 |
|
||||
| Large | 8 | 8 |
|
||||
| XL | 24 | 24 |
|
||||
| 2XL | 80 | 80 |
|
||||
| 4XL | 80 | 80 |
|
||||
| 8XL | 80 | 80 |
|
||||
| 12XL | 80 | 80 |
|
||||
| 16XL | 80 | 80 |
|
||||
| Plan | Max Replication Slots | Max WAL Senders |
|
||||
| ------ | --------------------- | --------------- |
|
||||
| Micro | 5 | 5 |
|
||||
| Small | 5 | 5 |
|
||||
| Medium | 5 | 5 |
|
||||
| Large | 8 | 8 |
|
||||
| XL | 24 | 24 |
|
||||
| 2XL | 80 | 80 |
|
||||
| 4XL | 80 | 80 |
|
||||
| 8XL | 80 | 80 |
|
||||
| 12XL | 80 | 80 |
|
||||
| 16XL | 80 | 80 |
|
||||
|
||||
<Admonition type="caution">
|
||||
|
||||
|
||||
@@ -51,7 +51,7 @@ Upgrading your organization to a paid plan means that you unlock the benefits of
|
||||
|
||||
## Usage-based billing for compute
|
||||
|
||||
We provide a dedicated server for every Supabase project. By default, your instance runs on the Starter Compute instance. You can upgrade your compute size in your [project settings](https://supabase.com/dashboard/project/_/settings/addons).
|
||||
We provide a dedicated server for every Supabase project. By default, your instance runs on the Micro Compute instance. You can upgrade your compute size in your [project settings](https://supabase.com/dashboard/project/_/settings/addons).
|
||||
|
||||
You won't get an immediate charge upfront when changing compute, instead we'll bill you based on compute runtime hours when your billing cycle resets.
|
||||
|
||||
@@ -67,7 +67,7 @@ We only count compute hours for instances that are active. Paused projects do no
|
||||
|
||||
| Instance Size | Hourly Price | Estimated Monthly Price |
|
||||
| ------------- | ------------ | ----------------------- |
|
||||
| Starter | $0.01344 | ~$10 |
|
||||
| Micro | $0.01344 | ~$10 |
|
||||
| Small | $0.0206 | ~$15 |
|
||||
| Medium | $0.0822 | ~$60 |
|
||||
| Large | $0.1517 | ~$110 |
|
||||
@@ -80,11 +80,11 @@ We only count compute hours for instances that are active. Paused projects do no
|
||||
|
||||
### Free plan
|
||||
|
||||
Supabase provides two "Free organizations". Each organization can run a `Starter` instance for free. This is a great way to get started with Supabase and try out the platform.
|
||||
Supabase provides two "Free organizations". Each organization can run a `Micro` instance for free. This is a great way to get started with Supabase and try out the platform.
|
||||
|
||||
### Compute credits
|
||||
|
||||
Paid plans come with $10 of Compute Credits to cover one Starter instance or parts of any other [Compute Add-On](/docs/guides/platform/compute-add-ons).
|
||||
Paid plans come with $10 of Compute Credits to cover one Micro instance or parts of any other [Compute Add-On](/docs/guides/platform/compute-add-ons).
|
||||
|
||||
Compute Credits are deducted from your Compute Usage. You can launch as many instances as you want on paid plans and we'll bill based on the compute hours. If you upgrade an instance for 24 hours, you'll only be billed for those 24 hours of additional compute. Compute hours are billed when you do plan up/downgrades (resets the billing cycle) or whenever your billing cycle resets once a month.
|
||||
|
||||
@@ -152,7 +152,7 @@ While you only pay for the $25 Pro plan once, launching additional projects at l
|
||||
| Line Item | Price |
|
||||
| ------------------------- | ----- |
|
||||
| Pro Plan for Organization | $25 |
|
||||
| Starter Compute x3 | $30 |
|
||||
| Micro Compute x3 | $30 |
|
||||
| Compute Credits | $-10 |
|
||||
| Total | $45 |
|
||||
|
||||
|
||||
@@ -241,7 +241,7 @@ const UpcomingInvoice = ({ slug }: UpcomingInvoiceProps) => {
|
||||
<td className="py-2 text-sm max-w-[200px]">
|
||||
<span className="mr-2">{computeCredits.description}</span>
|
||||
<InvoiceTooltip
|
||||
text="Paid plans come with $10 in Compute Credits to cover one Starter instance or parts of any other instance. Compute Credits are given to you every month and do not stack up while you are on a paid plan."
|
||||
text="Paid plans come with $10 in Compute Credits to cover one Micro instance or parts of any other instance. Compute Credits are given to you every month and do not stack up while you are on a paid plan."
|
||||
linkRef="https://supabase.com/docs/guides/platform/org-based-billing#compute-credits"
|
||||
/>
|
||||
</td>
|
||||
|
||||
@@ -462,7 +462,7 @@ const PlanUpdateSidePanel = () => {
|
||||
<div>
|
||||
<p className="text-sm mt-2">
|
||||
Each project is a dedicated server and database. Paid plans come with $10 of
|
||||
Compute Credits to cover one project on the default Starter Compute size or
|
||||
Compute Credits to cover one project on the default Micro Compute size or
|
||||
parts of any compute addon. Additional unpaused projects on paid plans will
|
||||
incur compute usage costs starting at $10 per month, billed hourly.
|
||||
</p>
|
||||
|
||||
@@ -69,7 +69,7 @@ const Compute = ({ orgSlug, projectRef, startDate, endDate }: ComputeProps) => {
|
||||
section={{
|
||||
name: 'Compute Hours',
|
||||
description:
|
||||
'Amount of hours your projects were active. Each project is a dedicated server and database.\nPaid plans come with $10 in Compute Credits to cover one project running on Starter Compute or parts of any compute add-on.\nBilling is based on the sum of Compute Hours used. Paused projects do not count towards usage.',
|
||||
'Amount of hours your projects were active. Each project is a dedicated server and database.\nPaid plans come with $10 in Compute Credits to cover one project running on Micro Compute or parts of any compute add-on.\nBilling is based on the sum of Compute Hours used. Paused projects do not count towards usage.',
|
||||
links: [
|
||||
{
|
||||
name: 'Compute Add-ons',
|
||||
|
||||
@@ -46,7 +46,7 @@ export const computeUsageMetricLabel = (computeUsageMetric: ComputeUsageMetric)
|
||||
case 'COMPUTE_HOURS_BRANCH':
|
||||
return 'Branches'
|
||||
case 'COMPUTE_HOURS_XS':
|
||||
return 'Starter'
|
||||
return 'Micro'
|
||||
case 'COMPUTE_HOURS_SM':
|
||||
return 'Small'
|
||||
case 'COMPUTE_HOURS_MD':
|
||||
|
||||
@@ -61,9 +61,9 @@ export default function ComputePricingModal({ showComputeModal, setShowComputeMo
|
||||
<p className="text-sm">
|
||||
Compute instances are billed hourly and you can scale up or down at any time if you
|
||||
need extra performance. You'll only be charged at the end of the month for the hours
|
||||
you've used. Paid plans come with $10 in Compute Credits to cover one Starter
|
||||
instance or parts of any other instance. Compute Credits are given to you not only
|
||||
for the first month but for every month while you are on a paid plan. Read more on{' '}
|
||||
you've used. Paid plans come with $10 in Compute Credits to cover one Micro instance
|
||||
or parts of any other instance. Compute Credits are given to you not only for the
|
||||
first month but for every month while you are on a paid plan. Read more on{' '}
|
||||
<Link
|
||||
href="https://supabase.com/docs/guides/platform/org-based-billing#usage-based-billing-for-compute"
|
||||
target="_blank"
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
"rows": [
|
||||
{
|
||||
"columns": [
|
||||
{ "key": "plan", "title": "Plan", "value": "Starter" },
|
||||
{ "key": "plan", "title": "Plan", "value": "Micro" },
|
||||
{ "key": "pricing", "title": "Price USD", "value": "$10" },
|
||||
{ "key": "cpu", "title": "CPU", "value": "2-core ARM" },
|
||||
{ "key": "dedicated", "title": "Dedicated", "value": false },
|
||||
|
||||
Reference in New Issue
Block a user