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

AutoGLM-Phone-9B-Multilingual

by zai-org

934K params · image-text-to-text · 229 likes · 14.1k downloads

AutoGLM-Phone-9B-Multilingual is a 934K parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (1405179 tok/s), GeForce RTX 5090 (2107234 tok/s), M4 Max 128GB (514212 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Novita62 tok/s

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB1405179 tok/scomfortable
GeForce RTX 509032GB2107234 tok/scomfortable
M4 Max 128GB128GB514212 tok/scomfortable
M4 Pro 48GB48GB257106 tok/scomfortable
M4 Pro 24GB24GB257106 tok/scomfortable
A100 PCIe 80 GB80GB2574486 tok/scomfortable
H100 SXM5 80 GB80GB5178082 tok/scomfortable
GeForce RTX 309024GB1242388 tok/scomfortable
Radeon RX 7900 XTX24GB1027397 tok/scomfortable
GeForce RTX 408016GB997260 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0