Skip to content
m.recipes
Find a configuration
Sign in
1 models with qualified results

Models

Measured configurations by model. Open a model to compare GPUs on one exact test.

Run this model

Choose your operating system and enter a model repository. Launch support is checked separately from performance results.

Reset

Speech recognition · All measured GPUs

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

  1. whisper-tiny

    openai · 7 tested configurations · 4 GPUs

    • RTX 3080 Ti · 12 GBfp16 · Audio → Text · asr_prompts · Test duration 2 s
      Throughput · Batch 1
      65.7audio-sec/sec
      Best measured · Batch 4
      91.8audio-sec/sec
      Observed GPU occupancy
      0.4GiB
      P95 latency
      Not recorded
      Evidence report and run availability ↗Same test on other GPUs
      Test details · 2 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
      faster-whisper · PyTorch 2.12.1+cu130
      Protocol
      audio-native-v1
      Dataset
      asr_prompts
      Workload
      asr
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B165.65——0.41134.913f8b97e6 ↗
      B491.84——0.4143.613f8b97e6 ↗
    • RTX PRO 6000 Blackwell Server Edition · 96 GBfp16 · Audio → Text · asr_prompts · Test duration 2 s
      Throughput · Batch 1
      233audio-sec/sec
      Best measured · Batch 4
      364audio-sec/sec
      Observed GPU occupancy
      1.4GiB
      P95 latency
      Not recorded
      Evidence report and run availability ↗Same test on other GPUs
      Test details · 2 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
      faster-whisper · PyTorch 2.14.1
      Protocol
      audio-native-v1
      Dataset
      asr_prompts
      Workload
      asr
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B1232.81——1.42113.52ba5a45ac ↗
      B4364.19——1.43115.82ba5a45ac ↗
    • V100-PCIE-32GB · 32 GBfp16 · Audio → Text · asr_prompts · Test duration 1 s
      Throughput · Batch 1
      105audio-sec/sec
      Best measured · Batch 4
      156audio-sec/sec
      Observed GPU occupancy
      0.5GiB
      P95 latency
      Not recorded
      Evidence report and run availability ↗Same test on other GPUs
      Test details · 2 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
      faster-whisper · PyTorch 2.12.1+cu126
      Protocol
      audio-native-v1
      Dataset
      asr_prompts
      Workload
      asr
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B1104.96——0.5151.5164035c7b ↗
      B4155.93——0.5250.1164035c7b ↗
    • 1 other test configurations on this GPU
      • fp16 · Audio → Text · asr_prompts · Test duration 5 s
        Throughput · Batch 1
        90.9audio-sec/sec
        Best measured · Batch 4
        132audio-sec/sec
        Observed GPU occupancy
        0.5GiB
        P95 latency
        Not recorded
        Evidence report and run availability ↗Same test on other GPUs
        Test details · 2 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
        faster-whisper · PyTorch 2.12.1+cu126
        Protocol
        audio-native-v1
        Dataset
        asr_prompts
        Workload
        asr
        Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B190.94——0.5151.510e4ef00c1 ↗
        B4132.16——0.5251.210e4ef00c1 ↗
    Show 1 more GPUs
    • vGPU-32GB · 32 GBfp16 · Audio → Text · asr_prompts
      Throughput · Batch 1
      73.7audio-sec/sec
      Observed GPU occupancy
      0.4GiB
      P95 latency
      Not recorded
      Evidence report and run availability ↗Same test on other GPUs
      Test details · 2 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
      faster-whisper · PyTorch 2.13.0+cu130
      Protocol
      audio-native-v1
      Dataset
      asr_prompts
      Workload
      asr
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B173.68——0.3846.817d182de2 ↗
      B468.2——0.3849.217d182de2 ↗
    • 2 other test configurations on this GPU
      • fp16 · Audio → Text · asr_prompts · Test duration 4 s
        Throughput · Batch 1
        122audio-sec/sec
        Best measured · Batch 4
        168audio-sec/sec
        Observed GPU occupancy
        0.4GiB
        P95 latency
        Not recorded
        Evidence report and run availability ↗Same test on other GPUs
        Test details · 2 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
        faster-whisper
        Protocol
        audio-native-v1
        Dataset
        asr_prompts
        Workload
        asr
        Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B1121.9——0.4273.617aaa1f0d ↗
        B4168.25——0.4277.417aaa1f0d ↗
      • fp16 · Audio → Text · asr_prompts · Test duration 1 s
        Throughput · Batch 1
        137audio-sec/sec
        Best measured · Batch 4
        205audio-sec/sec
        Observed GPU occupancy
        0.4GiB
        P95 latency
        Not recorded
        Evidence report and run availability ↗Same test on other GPUs
        Test details · 2 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
        faster-whisper · PyTorch 2.13.0+cu130
        Protocol
        audio-native-v1
        Dataset
        asr_prompts
        Workload
        asr
        Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B1137.01——0.3854.314b83f25d ↗
        B4205.27——0.3866.314b83f25d ↗
Sortable tables by exact test condition · 14 rows
Speech recognition · Audio → Text · asr_prompts · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisperPyTorch 2.13.0+cu13073.68——0.3846.817d182de2 ↗
Speech recognition · Audio → Text · asr_prompts · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisperPyTorch 2.13.0+cu13068.2——0.3849.217d182de2 ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 1 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyV100-PCIE-32GB · 32 GBfp16faster-whisperPyTorch 2.12.1+cu126104.96——0.5151.5164035c7b ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 1 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisperPyTorch 2.13.0+cu130137.01——0.3854.314b83f25d ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 1 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyV100-PCIE-32GB · 32 GBfp16faster-whisperPyTorch 2.12.1+cu126155.93——0.5250.1164035c7b ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 1 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisperPyTorch 2.13.0+cu130205.27——0.3866.314b83f25d ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 2 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyRTX 3080 Ti · 12 GBfp16faster-whisperPyTorch 2.12.1+cu13065.65——0.41134.913f8b97e6 ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 2 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyRTX PRO 6000 Blackwell Server Edition · 96 GBfp16faster-whisperPyTorch 2.14.1232.81——1.42113.52ba5a45ac ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 2 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyRTX 3080 Ti · 12 GBfp16faster-whisperPyTorch 2.12.1+cu13091.84——0.4143.613f8b97e6 ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 2 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyRTX PRO 6000 Blackwell Server Edition · 96 GBfp16faster-whisperPyTorch 2.14.1364.19——1.43115.82ba5a45ac ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 4 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisper121.9——0.4273.617aaa1f0d ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 4 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyvGPU-32GB · 32 GBfp16faster-whisper168.25——0.4277.417aaa1f0d ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 5 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyV100-PCIE-32GB · 32 GBfp16faster-whisperPyTorch 2.12.1+cu12690.94——0.5151.510e4ef00c1 ↗
Speech recognition · Audio → Text · asr_prompts · Test duration 5 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
whisper-tinyV100-PCIE-32GB · 32 GBfp16faster-whisperPyTorch 2.12.1+cu126132.16——0.5251.210e4ef00c1 ↗