Run an AI model on your computer
Get a startup command, then explore measured performance for your task and GPU.
Get your startup command
Choose your operating system and enter a model repository. Launch support is checked separately from performance results.
All tasks · vGPU-32GB · 32 GB
4 models with qualified results. Speeds compare only within one exact test; use “Same test on other GPUs” to compare hardware.
embeddinggemma-2
google · 5 tested configurations
- bf16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 9 s
- Throughput · Batch 1
- 251vectors/sec
- Best measured · Batch 16
- 2,710vectors/sec
- Observed GPU occupancy
- 1GiB
- P95 latency
- 4 ms
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 2.13.0+cu130
- Protocol
- native-forward-v1
- Dataset
- embedding-mteb-tasks-v1
- Workload
- embedding
Batch size Mean throughput (vectors/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 251.11 4 ms — 1.05 99.4 1 f489c748 ↗ B4 924.83 4 ms — 1.05 111.5 1 f489c748 ↗ B16 2,710.19 6 ms — 1.05 114.9 1 f489c748 ↗ 4 other test configurations on this GPU
- bf16 · Text → Vectors · embedding-sanity-v1 · Test duration 6 s
- Throughput · Batch 1
- 38.3vectors/sec
- Best measured · Batch 4
- 139vectors/sec
- Observed GPU occupancy
- 0.8GiB
- P95 latency
- 31 ms
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
- sentence-transformers · PyTorch 2.13.0+cu130
- Protocol
- native-forward-v1
- Dataset
- embedding-sanity-v1
- Workload
- embedding
Batch size Mean throughput (vectors/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 38.33 31 ms — 0.82 50.5 4 2c17d254 ↗ B4 138.64 33 ms — 0.82 54.2 4 2c17d254 ↗ - bf16 · Text → Vectors · embedding-sanity-v1 · Test duration 12 s
- Throughput · Batch 1
- 38.8vectors/sec
- Best measured · Batch 64
- 1,766vectors/sec
- Observed GPU occupancy
- 0.8GiB
- P95 latency
- 27 ms
Test details · 4 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 2.13.0+cu130
- Protocol
- native-forward-v1
- Dataset
- embedding-sanity-v1
- Workload
- embedding
Batch size Mean throughput (vectors/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 38.8 27 ms — 0.82 48.8 1 dc5960cd ↗ B4 141.65 29 ms — 0.82 52.4 1 dc5960cd ↗ B16 553.54 30 ms — 0.87 56.4 1 dc5960cd ↗ B64 1,766.47 38 ms — 1.03 65.3 1 dc5960cd ↗ - bf16 · Text → Vectors · embedding-sanity-v1 · Test duration 6 s
- Throughput · Batch 1
- 38.3vectors/sec
- Best measured · Batch 4
- 138vectors/sec
- Observed GPU occupancy
- 0.8GiB
- P95 latency
- 32 ms
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
- sentence-transformers
- Protocol
- native-forward-v1
- Dataset
- embedding-sanity-v1
- Workload
- embedding
Batch size Mean throughput (vectors/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 38.27 32 ms — 0.82 48.6 1 47f71b64 ↗ B4 137.82 35 ms — 0.82 51.9 1 47f71b64 ↗ - bf16 · Text → Vectors · embedding-sanity-v1
- Throughput · Batch 1
- 39.4vectors/sec
- Best measured · Batch 4
- 120vectors/sec
- Observed GPU occupancy
- Not recorded
- P95 latency
- 26 ms
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
- sentence-transformers
- Protocol
- native-forward-v1
- Dataset
- embedding-sanity-v1
- Workload
- embedding
Batch size Mean throughput (vectors/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 39.4 26 ms — — — 1 2c97c869 ↗ B4 119.85 44 ms — — — 1 2c97c869 ↗
Kokoro-82M
hexgrad · 3 tested configurations
- fp32 · 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
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 43.43 101 ms — 0.99 64.1 1 d8e4b3ce ↗ B4 44.88 396 ms — 1.03 69.1 1 d8e4b3ce ↗ 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
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 40.36 104 ms — 0.99 60.5 1 c0488108 ↗ B4 41.8 426 ms — 1.03 65.9 1 c0488108 ↗ - 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
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 76.72 45 ms — 1 83.5 1 d90a5c29 ↗ B2 79.84 100 ms — 1.03 100.8 1 d90a5c29 ↗
whisper-tiny
openai · 3 tested configurations
- fp16 · Audio → Text · asr_prompts
- Throughput · Batch 1
- 73.7audio-sec/sec
- Observed GPU occupancy
- 0.4GiB
- P95 latency
- Not recorded
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 73.68 — — 0.38 46.8 1 7d182de2 ↗ B4 68.2 — — 0.38 49.2 1 7d182de2 ↗ 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
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 121.9 — — 0.42 73.6 1 7aaa1f0d ↗ B4 168.25 — — 0.42 77.4 1 7aaa1f0d ↗ - 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
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 size Mean throughput (audio-sec/sec) P95 TTFT Observed occupancy (GiB) GPU power (W) Reports combined View report B1 137.01 — — 0.38 54.3 1 4b83f25d ↗ B4 205.27 — — 0.38 66.3 1 4b83f25d ↗
Models shown: 3 / 4
Recipe availability is checked on each report against the published recipe executor.
Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.
Measured hardware
- L4 · 24 GB
- RTX 3080 Ti · 12 GB
- RTX 4090 · 24 GB
- RTX 5090 · 32 GB
- RTX PRO 6000 Blackwell Server Edition · 96 GB
- T4 · 16 GB
- V100-PCIE-32GB · 32 GB
- vGPU-32GB · 32 GB
13 more GPUs without qualified results for this task
Running benchmarks
0Updates automaticallyNo benchmarks are currently reported as running.
RTX PRO 6000 Blackwell Server Edition · 96 GB · 403 queued · 0 running · 0 awaiting reassignment · 6 succeeded · 3 failed or exhausted
L4 · 24 GB · 91 queued · 0 running · 0 awaiting reassignment · 22 succeeded · 7 failed or exhausted
T4 · 16 GB · 22 queued · 0 running · 0 awaiting reassignment · 3 succeeded · 8 failed or exhausted