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

c4ai-command-r-plus

by CohereLabs

104B params · text-generation · 1.8k likes · 5.0k downloads

c4ai-command-r-plus is a 104B parameter model. At Q4 quantization it requires 52GB of VRAM. It runs comfortably on H100 SXM5 80 GB (46 tok/s), H200 SXM 141 GB (67 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
M4 Max 128GB128GB4 tok/stight
A100 PCIe 80 GB80GB23 tok/stight
H100 SXM5 80 GB80GB46 tok/scomfortable
M4 Max 64GB64GB4 tok/stight
H200 SXM 141 GB141GB67 tok/scomfortable
M2 Ultra 192GB192GB6 tok/stight
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0