R_REDDYX.XYZ
AIPython★ 320⑂ 26 forksApache-2.0

Picovoice/picollm

PICOLLM - OFFLINE LLM ON DEVICE

picollm enables running LLM on-device through extreme k‑bit quantization, delivering fast and private inference without the cloud.

// KEY FEATURES

  • X‑bit quantization reduces model size to 2‑bits
  • Run LLM on-device without internet or GPU
  • Compatible with HuggingFace and Transformers Python packages
#compression#efficient-inference#gemma#generative-ai#language-model#language-models#large-language-model#llama#llama2#llama3#llm#llm-inference
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

AGENT TRADE KIT: OKX AI★ 320Godot AI Chat with MCP★ 320DELPHIOPENAI – API FOR DELPHI★ 320MCP-SERVER BITWARDEN MANAGEMENT★ 320GUUARDVARK LOCAL AI WORKSTATION★ 320WRIT: MANAGING AGENT★ 320

← FULL CATALOG

Picovoice/picollm — Picollm - Offline LLM ON Device