Skip to content
m.recipes
Find a configuration
Sign in
80 GB · 7 reports

A100-SXM4-80GB · 80 GB

Qualified results first; original reports and full tables stay below.
Reset

Embedding · Qualified results

Speeds compare only within one exact test. Recipe availability is checked on each report against the published recipe executor.

No qualified results yet · Embedding · A100-SXM4-80GB · 80 GB

No reports for this task have been recorded here. This does not show that the model or GPU cannot run it.

Check model launch supportMeasured alternatives for this taskTest your own GPU

Measured alternatives on other GPUs

Measured on different GPUs with the same or smaller listed capacity. These are references for choosing hardware, not performance or compatibility evidence for your selected GPU.

  1. Qwen3-Embedding-4B

    Qwen · 4 tested configurations · 2 GPUs

    • RTX 4090 · 24 GBfp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 3 s
      Throughput · Batch 16
      498vectors/sec
      Observed GPU occupancy
      8.2GiB
      P95 latency
      33 ms
      Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
      Test details

      Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

      Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

      Engine
      sentence-transformers · PyTorch 2.12.1+cu126
      Protocol
      native-forward-v1
      Dataset
      embedding-mteb-tasks-v1
      Workload
      embedding
      Batch sizeMean throughput (vectors/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B16497.8433 ms—8.22262.810d6d756e ↗
    • 1 other test configurations on this GPU
      • fp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s
        Throughput · Batch 1
        81.2vectors/sec
        Best measured · Batch 16
        507vectors/sec
        Observed GPU occupancy
        8.3GiB
        P95 latency
        12 ms
        Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
        Test details · 3 batch sizes

        Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

        Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

        Engine
        sentence-transformers · PyTorch 2.12.1+cu126
        Protocol
        native-forward-v1
        Dataset
        embedding-mteb-tasks-v1
        Workload
        embedding
        Batch sizeMean throughput (vectors/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B181.1912 ms—8.34258.914f6f3fbb ↗
        B4279.3114 ms—8.34270.514f6f3fbb ↗
        B16507.0432 ms—8.34264.414f6f3fbb ↗
    Show 1 more GPUs
    • V100-PCIE-32GB · 32 GBfp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 9 s
      Throughput · Batch 1
      41vectors/sec
      Best measured · Batch 16
      229vectors/sec
      Observed GPU occupancy
      8.2GiB
      P95 latency
      25 ms
      Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
      Test details · 3 batch sizes

      Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

      Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

      Engine
      sentence-transformers · PyTorch 2.12.1+cu126
      Protocol
      native-forward-v1
      Dataset
      embedding-mteb-tasks-v1
      Workload
      embedding
      Batch sizeMean throughput (vectors/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B140.9625 ms—8.25119.3165a1050f ↗
      B4100.3740 ms—8.25149.9165a1050f ↗
      B16228.9270 ms—8.25178.1165a1050f ↗
    • 1 other test configurations on this GPU
      • fp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s
        Throughput · Batch 1
        40.9vectors/sec
        Best measured · Batch 16
        228vectors/sec
        Observed GPU occupancy
        8.2GiB
        P95 latency
        25 ms
        Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
        Test details · 3 batch sizes

        Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

        Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

        Engine
        sentence-transformers · PyTorch 2.12.1+cu126
        Protocol
        native-forward-v1
        Dataset
        embedding-mteb-tasks-v1
        Workload
        embedding
        Batch sizeMean throughput (vectors/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B140.9425 ms—8.25123.41cd3861d6 ↗
        B4100.2340 ms—8.25146.91cd3861d6 ↗
        B16228.3570 ms—8.25180.41cd3861d6 ↗

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Original reports

Every report for this task, including quality, diagnostic and legacy runs that do not enter comparisons.
Original reports · 0 rows
ModelTest taskFormatEngineWorkloadProtocolQuality scoreTest date
No matching results

Running benchmarks

0Updates automatically

No benchmarks are currently reported as running.

Methodology

Average of error-free runs for the selected recorded configuration. Missing methods and fallback runs are not ranked. Performance index = average / fastest matching hardware × 100. Value index = performance per purchase cost / best comparable value × 100. Quality is separate by dataset and protocol. Prices are dated seller listings, not completed transactions or market averages.

Updated 11/6/2026, 4:54:35 PM