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

snowflake-arctic-embed-l

by Snowflake

334M params · sentence-similarity · 100 likes · 22.4k downloads

snowflake-arctic-embed-l is a 334M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (3930 tok/s), GeForce RTX 5090 (5893 tok/s), M4 Max 128GB (1438 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB3930 tok/scomfortable
GeForce RTX 509032GB5893 tok/scomfortable
M4 Max 128GB128GB1438 tok/scomfortable
M4 Pro 48GB48GB719 tok/scomfortable
M4 Pro 24GB24GB719 tok/scomfortable
A100 PCIe 80 GB80GB7200 tok/scomfortable
H100 SXM5 80 GB80GB14482 tok/scomfortable
GeForce RTX 309024GB3474 tok/scomfortable
Radeon RX 7900 XTX24GB2873 tok/scomfortable
GeForce RTX 408016GB2789 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0