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

TinyLlama-1.1B-step-50K-105b

by TinyLlama

1.1B params · text-generation · 134 likes · 14.7k downloads

TinyLlama-1.1B-step-50K-105b is a 1.1B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (1193 tok/s), GeForce RTX 5090 (1789 tok/s), M4 Max 128GB (436 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Featherless

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB1193 tok/scomfortable
GeForce RTX 509032GB1789 tok/scomfortable
M4 Max 128GB128GB436 tok/scomfortable
M4 Pro 48GB48GB218 tok/scomfortable
M4 Pro 24GB24GB218 tok/scomfortable
A100 PCIe 80 GB80GB2186 tok/scomfortable
H100 SXM5 80 GB80GB4398 tok/scomfortable
GeForce RTX 309024GB1055 tok/scomfortable
Radeon RX 7900 XTX24GB872 tok/scomfortable
GeForce RTX 408016GB847 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0