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

DeBERTa-v3-large-mnli-fever-anli-ling-wanli

by MoritzLaurer

435M params · zero-shot-classification · 119 likes · 177.9k downloads

DeBERTa-v3-large-mnli-fever-anli-ling-wanli is a 435M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (3017 tok/s), GeForce RTX 5090 (4525 tok/s), M4 Max 128GB (1104 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB3017 tok/scomfortable
GeForce RTX 509032GB4525 tok/scomfortable
M4 Max 128GB128GB1104 tok/scomfortable
M4 Pro 48GB48GB552 tok/scomfortable
M4 Pro 24GB24GB552 tok/scomfortable
A100 PCIe 80 GB80GB5529 tok/scomfortable
H100 SXM5 80 GB80GB11121 tok/scomfortable
GeForce RTX 309024GB2668 tok/scomfortable
Radeon RX 7900 XTX24GB2206 tok/scomfortable
GeForce RTX 408016GB2141 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0