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

Models

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

Get your startup command

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

Reset

Speech synthesis · All measured GPUs

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

  1. IndexTTS-2.5

    IndexTeam · 1 tested configuration · 1 GPU

    • RTX PRO 6000 Blackwell Server Edition · 96 GBNative · Not recorded → Audio · tts_prompts · Test duration 9 s
      Throughput · Batch 1
      4.2audio-sec/sec
      Observed GPU occupancy
      6.5GiB
      P95 latency
      Not recorded
      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
      indextts · PyTorch 2.8.0+cu128
      Protocol
      audio-native-v1
      Dataset
      tts_prompts
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B14.24——6.48221.71a46ec2c4 ↗

  2. Qwen3-TTS-12Hz-0.6B-CustomVoice

    Qwen · 1 tested configuration · 1 GPU

    • RTX PRO 6000 Blackwell Server Edition · 96 GBNative · Not recorded → Audio · tts_prompts · Test duration 43 s
      Throughput · Batch 1
      1.6audio-sec/sec
      Best measured · Batch 4
      5.2audio-sec/sec
      Observed GPU occupancy
      3.3GiB
      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
      qwen-tts · PyTorch 2.14.1
      Protocol
      audio-native-v1
      Dataset
      tts_prompts
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B11.6——3.34154.41ebb272f8 ↗
      B45.22——4.921611ebb272f8 ↗

  3. magpie_tts_multilingual_357m

    nvidia · 1 tested configuration · 1 GPU

    • RTX PRO 6000 Blackwell Server Edition · 96 GBNative · Not recorded → Audio · tts_prompts · Test duration 19 s
      Throughput · Batch 1
      3.6audio-sec/sec
      Observed GPU occupancy
      4GiB
      P95 latency
      Not recorded
      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
      nemo-magpie · PyTorch 2.13.0
      Protocol
      audio-native-v1
      Dataset
      tts_prompts
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B13.57——4.01178.81666efb0f ↗

  4. Kokoro-82M

    hexgrad · 6 tested configurations · 4 GPUs

    • RTX 3080 Ti · 12 GBfp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
      Throughput · Batch 1
      49.2audio-sec/sec
      Best measured · Batch 2
      52.8audio-sec/sec
      Observed GPU occupancy
      1GiB
      P95 latency
      73 ms
      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
      kokoro · PyTorch 2.12.1+cu130
      Protocol
      audio-native-v1
      Dataset
      kokoro-english-v1
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B149.1873 ms—1158.913c7db092 ↗
      B252.8140 ms—1.06194.713c7db092 ↗
    • RTX PRO 6000 Blackwell Server Edition · 96 GBfp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
      Throughput · Batch 1
      120audio-sec/sec
      Best measured · Batch 4
      125audio-sec/sec
      Observed GPU occupancy
      2GiB
      P95 latency
      29 ms
      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
      kokoro · PyTorch 2.13.0+cu130
      Protocol
      audio-native-v1
      Dataset
      kokoro-english-v1
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B1120.329 ms—2152.12061d047a ↗
      B4125.19124 ms—2.03169.72061d047a ↗
    • V100-PCIE-32GB · 32 GBfp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
      Throughput · Batch 1
      36audio-sec/sec
      Best measured · Batch 2
      37.8audio-sec/sec
      Observed GPU occupancy
      1.4GiB
      P95 latency
      105 ms
      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
      kokoro · PyTorch 2.12.1+cu126
      Protocol
      audio-native-v1
      Dataset
      kokoro-english-v1
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B135.95105 ms—1.4576.311b40f8533 ↗
      B237.83237 ms—1.4582.611b40f8533 ↗
    Show 1 more GPUs
    • vGPU-32GB · 32 GBfp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
      Throughput · Batch 1
      43.4audio-sec/sec
      Best measured · Batch 4
      44.9audio-sec/sec
      Observed GPU occupancy
      1GiB
      P95 latency
      101 ms
      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
      kokoro
      Protocol
      audio-native-v1
      Dataset
      kokoro-english-v1
      Workload
      tts
      Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B143.43101 ms—0.9964.11d8e4b3ce ↗
      B444.88396 ms—1.0369.11d8e4b3ce ↗
    • 2 other test configurations on this GPU
      • fp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
        Throughput · Batch 1
        40.4audio-sec/sec
        Best measured · Batch 4
        41.8audio-sec/sec
        Observed GPU occupancy
        1GiB
        P95 latency
        104 ms
        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
        kokoro · PyTorch 2.13.0+cu130
        Protocol
        audio-native-v1
        Dataset
        kokoro-english-v1
        Workload
        tts
        Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B140.36104 ms—0.9960.51c0488108 ↗
        B441.8426 ms—1.0365.91c0488108 ↗
      • fp32 · Text → Audio · kokoro-english-v1 · Test duration 6 s
        Throughput · Batch 1
        76.7audio-sec/sec
        Best measured · Batch 2
        79.8audio-sec/sec
        Observed GPU occupancy
        1GiB
        P95 latency
        45 ms
        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
        kokoro · PyTorch 2.13.0+cu130
        Protocol
        audio-native-v1
        Dataset
        kokoro-english-v1
        Workload
        tts
        Batch sizeMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B176.7245 ms—183.51d90a5c29 ↗
        B279.84100 ms—1.03100.81d90a5c29 ↗
Sortable tables by exact test condition · 16 rows
Speech synthesis · Not recorded → Audio · tts_prompts · Test duration 9 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
IndexTTS-2.5RTX PRO 6000 Blackwell Server Edition · 96 GBNativeindexttsPyTorch 2.8.0+cu1284.24——6.48221.71a46ec2c4 ↗
Speech synthesis · Not recorded → Audio · tts_prompts · Test duration 19 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
magpie_tts_multilingual_357mRTX PRO 6000 Blackwell Server Edition · 96 GBNativenemo-magpiePyTorch 2.13.03.57——4.01178.81666efb0f ↗
Speech synthesis · Not recorded → Audio · tts_prompts · Test duration 43 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Qwen3-TTS-12Hz-0.6B-CustomVoiceRTX PRO 6000 Blackwell Server Edition · 96 GBNativeqwen-ttsPyTorch 2.14.11.6——3.34154.41ebb272f8 ↗
Speech synthesis · Not recorded → Audio · tts_prompts · Test duration 43 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Qwen3-TTS-12Hz-0.6B-CustomVoiceRTX PRO 6000 Blackwell Server Edition · 96 GBNativeqwen-ttsPyTorch 2.14.15.22——4.921611ebb272f8 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MRTX 3080 Ti · 12 GBfp32kokoroPyTorch 2.12.1+cu13049.1873 ms—1158.913c7db092 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MRTX PRO 6000 Blackwell Server Edition · 96 GBfp32kokoroPyTorch 2.13.0+cu130120.329 ms—2152.12061d047a ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MV100-PCIE-32GB · 32 GBfp32kokoroPyTorch 2.12.1+cu12635.95105 ms—1.4576.311b40f8533 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoro43.43101 ms—0.9964.11d8e4b3ce ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoroPyTorch 2.13.0+cu13040.36104 ms—0.9960.51c0488108 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 1 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoroPyTorch 2.13.0+cu13076.7245 ms—183.51d90a5c29 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 2 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MRTX 3080 Ti · 12 GBfp32kokoroPyTorch 2.12.1+cu13052.8140 ms—1.06194.713c7db092 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 2 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MV100-PCIE-32GB · 32 GBfp32kokoroPyTorch 2.12.1+cu12637.83237 ms—1.4582.611b40f8533 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 2 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoroPyTorch 2.13.0+cu13079.84100 ms—1.03100.81d90a5c29 ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MRTX PRO 6000 Blackwell Server Edition · 96 GBfp32kokoroPyTorch 2.13.0+cu130125.19124 ms—2.03169.72061d047a ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoro44.88396 ms—1.0369.11d8e4b3ce ↗
Speech synthesis · Text → Audio · kokoro-english-v1 · Test duration 6 s · Batch 4 · audio-sec/sec · 1 rows
ModelHardwareFormatEngineMean throughput (audio-sec/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Kokoro-82MvGPU-32GB · 32 GBfp32kokoroPyTorch 2.13.0+cu13041.8426 ms—1.0365.91c0488108 ↗
Models with reports but no qualified results · 1

Their original reports remain available on each model page. They did not qualify for comparison; each report states why.

Models with reports but no qualified results · 1 rows
ModelTest task
ChatTTS2Noise/ChatTTSSpeech synthesis