vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

text2vec-base-chinese

by shibing624

102M params · sentence-similarity · 784 likes · 409.8k downloads

text2vec-base-chinese is a 102M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (12838 tok/s), GeForce RTX 5090 (19253 tok/s), M4 Max 128GB (4698 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
HF Inference

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB12838 tok/scomfortable
GeForce RTX 509032GB19253 tok/scomfortable
M4 Max 128GB128GB4698 tok/scomfortable
M4 Pro 48GB48GB2349 tok/scomfortable
M4 Pro 24GB24GB2349 tok/scomfortable
A100 PCIe 80 GB80GB23522 tok/scomfortable
H100 SXM5 80 GB80GB47310 tok/scomfortable
GeForce RTX 309024GB11351 tok/scomfortable
Radeon RX 7900 XTX24GB9387 tok/scomfortable
GeForce RTX 408016GB9111 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0