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

financial-summarization-pegasus

by human-centered-summarization

569M params · summarization · 141 likes · 3.8k downloads

financial-summarization-pegasus is a 569M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (2308 tok/s), GeForce RTX 5090 (3461 tok/s), M4 Max 128GB (844 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB2308 tok/scomfortable
GeForce RTX 509032GB3461 tok/scomfortable
M4 Max 128GB128GB844 tok/scomfortable
M4 Pro 48GB48GB422 tok/scomfortable
M4 Pro 24GB24GB422 tok/scomfortable
A100 PCIe 80 GB80GB4229 tok/scomfortable
H100 SXM5 80 GB80GB8506 tok/scomfortable
GeForce RTX 309024GB2040 tok/scomfortable
Radeon RX 7900 XTX24GB1687 tok/scomfortable
GeForce RTX 408016GB1638 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0