granite-4.1-3b-llmon-preview: hardware requirements

No quantized files for granite-4.1-3b-llmon-preview have been published yet, so its memory need is not available. We list only sizes measured from real files.

Parameters
3.7B
Tier
Runs on a laptop
Licence
See model card
Released
2026-04-29

Will it run on your machine?

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

QuantDownloadRAM @ 4KRAM @ 32KSource

Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).

Other sizes of Granite 4.1 30B

Model card on HuggingFace →API specs & pricing →Verified 2026-11-13Listed for 120 days after release