Model reference · open weights

CmdCaliper

Embeddings CyCraftAI Embeddings 1 build Licence not stated 1k dl/mo

CmdCaliper is an open-weight embedding model from CyCraftAI. CmdCaliper-base (FP32) weighs 219 MB; the smallest configuration that runs it is RTX 3060 12 GB.

  • CmdCaliper-base is a 109M parameter embedding model developed by CyCraftAI for the sentence-similarity task.
  • It is specifically designed to process Windows command lines for security research, with inputs truncated to a maximum of 512 tokens.
  • The model was introduced in an EMNLP 2024 paper and is available as part of a family of three sizes.

Summary of the CyCraftAI/CmdCaliper-base model card, 2026-10-01

What it is

Released byCyCraftAI
Released2024-09-25
Parameters109M
VRAM219 MB for the weights

What it runs on

Memory and cards for CmdCaliper-base (FP32)

219 MBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together, which is the basis of search and RAG.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms