cpu
bitnet.cpp Tool
Microsoft's official inference framework for 1.58-bit ternary language models, built on llama.cpp with optimized CPU and GPU kernels for running very heavily compressed models on ordinary hardware.
Whistle Tool
Earlier-release roundup: October 2 CPU speech model with a 16.9 MB download, up to 30-second clips, and seven European languages. Useful for compact offline integrations, with documented quality trade-offs.
SHADOW-50M Tool
A proof-of-concept 44M-parameter CPU model with exact arithmetic circuits, disk-backed retrieval and WebAssembly support.
Mistral Timestral Tool
Four released forecasting models with public inference code and CPU execution; weights use a Modified MIT license and inference code uses Apache 2.0.
Kitten-TTS 2 Tool
Speech model with voice cloning from 5–30 seconds of audio and documented CPU inference, under the Stellon Labs Community License; disk size unverified and GPU-memory requirement unstated.
Indra OCR Tool
Shipping CPU OCR package with an approximately 76 MB default model download; no GPU required. Code is Apache 2.0, while model weights have separate commercial restrictions.