1 GPU on the selected test

embeddinggemma-2

GPUs are compared only on one exact test of this model. Change the test to see other conditions.

Test conditions

Every GPU below ran exactly these conditions.

Task: Embedding · Text → Vectors
Workload: Text → Vectors · embedding-sanity-v1 · Test duration 6 s
Batch size: Batch 1
Format · Engine: bf16 · sentence-transformers
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-sanity-v1 · embedding

GPUs on this test

Only one GPU configuration has matching measurements; a cross-hardware comparison is not yet available.

vGPU-32GB · 32 GB
Mean throughput
38.3vectors/sec
Observed GPU occupancy
0.8GiB
P95 latency
32 ms
Reports combined
1
Runs, parameters and setup ↗

Sortable table

Hardware ranking · 1 rows
Hardware	Mean throughput (vectors/sec)	P95 (s)	TTFT (ms)	Observed occupancy (GiB)	GPU power (W)	Throughput / W	VRAM per GPU (GB)	Reports combined
#1vGPU-32GB · 32 GBRuns, parameters and setup ↗	38.27	0.032	—	0.82	48.61	0.79	32	1

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, 11:07:29 PM