Run an AI model on your computer

Measured alternatives on other GPUs

Measured on different GPUs with the same or smaller listed capacity. These are references for choosing hardware, not performance or compatibility evidence for your selected GPU.

1. Qwen3-Embedding-0.6B

   Qwen · 1 tested configuration · 1 GPU

   • RTX 4090 · 24 GBfp16 · Text → Vectors · embedding-mteb-tasks-v1 · Test duration 90 s

     Throughput · Batch 1

     259vectors/sec

     Best measured · Batch 16

     2,018vectors/sec

     Observed GPU occupancy

     1.8GiB

     P95 latency

     4 ms

     Use this recipe · Batch 16 ↗Evidence report and run availability ↗Same test on other GPUs
     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 2.12.1+cu126

     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	258.52	4 ms	—	1.84	151.6	1	3ba3d2cb ↗
     B4	921.44	4 ms	—	1.84	159.5	1	3ba3d2cb ↗
     B16	2,017.74	8 ms	—	1.84	133	1	3ba3d2cb ↗