embeddinggemma-2
Run this model
Choose your operating system and enter a model repository. Launch support is checked separately from performance results.
Test conditions
- Task
- Embedding · Text → Vectors
- Workload
- Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s
- Batch size
- Batch 1
- Format · Engine
- nf4 · sentence-transformers · PyTorch 2.12.1+cu126
- Unit
- vectors/sec
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.
Protocol details
native-forward-v1 · embedding-mteb-tasks-v1 · embedding
GPUs on this test
- Mean throughput
- 175vectors/sec
- Observed GPU occupancy
- 0.9GiB
- P95 latency
- 6 ms
- Reports combined
- 5
- Mean throughput
- 90.1vectors/sec
- Observed GPU occupancy
- 0.7GiB
- P95 latency
- 11 ms
- Reports combined
- 2
Sortable table
| Hardware | Mean throughput (vectors/sec) | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Throughput / W | VRAM per GPU (GB) | Reports combined |
|---|---|---|---|---|---|---|---|---|
| #1L4 · 24 GBPyTorch 2.12.1+cu126Runs, parameters and setup ↗ | 174.95 | 0.006 | — | 0.85 | 54.79 | 3.19 | 24 | 5 |
| #2T4 · 16 GBPyTorch 2.12.1+cu126Runs, parameters and setup ↗ | 90.07 | 0.011 | — | 0.75 | 56.22 | 1.6 | 16 | 2 |
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.
How results are grouped
Results merge successful runs of the same model, precision and workload. CPU thread counts and CUDA wheel builds may differ; actual PyTorch builds are shown. Other recorded protocol settings remain separate.
Updated 11/5/2026, 11:06:29 PM