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

SmolLM2-1.7B-Instruct

by HuggingFaceTB

1.8B params · text-generation · 720 likes · 116.3k downloads

SmolLM2-1.7B-Instruct is a 1.8B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (724 tok/s), GeForce RTX 5090 (1086 tok/s), M4 Max 128GB (265 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB724 tok/scomfortable
GeForce RTX 509032GB1086 tok/scomfortable
M4 Max 128GB128GB265 tok/scomfortable
M4 Pro 48GB48GB132 tok/scomfortable
M4 Pro 24GB24GB132 tok/scomfortable
A100 PCIe 80 GB80GB1327 tok/scomfortable
H100 SXM5 80 GB80GB2670 tok/scomfortable
GeForce RTX 309024GB640 tok/scomfortable
Radeon RX 7900 XTX24GB529 tok/scomfortable
GeForce RTX 408016GB514 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0