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

SpatialLM-Llama-1B

by manycore-research

1.6B params · text-generation · 993 likes · 253 downloads

SpatialLM-Llama-1B is a 1.6B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (821 tok/s), GeForce RTX 5090 (1231 tok/s), M4 Max 128GB (300 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB821 tok/scomfortable
GeForce RTX 509032GB1231 tok/scomfortable
M4 Max 128GB128GB300 tok/scomfortable
M4 Pro 48GB48GB150 tok/scomfortable
M4 Pro 24GB24GB150 tok/scomfortable
A100 PCIe 80 GB80GB1504 tok/scomfortable
H100 SXM5 80 GB80GB3025 tok/scomfortable
GeForce RTX 309024GB725 tok/scomfortable
Radeon RX 7900 XTX24GB600 tok/scomfortable
GeForce RTX 408016GB582 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0