Skip to content
TechIndexSubmit
Back to directory

Ternary LLM Optimizer

An optimizer for training large language models that significantly reduces VRAM requirements, enabling training of 27B models on consumer GPUs. It focuses on ternary networks to match full precision quality.

Similar tools

  • Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel fusion, autotuning, and advanced scheduling. Run benchmarks across different GPU types and configurations, track results and share experiments with the community.

    Dev Tools
  • Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

    Dev Tools
  • A high-throughput and memory-efficient inference and serving engine for LLMs

    Models
  • A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

    Dev Tools
  • A language for constraint-guided and efficient LLM programming.

    AI Apps
  • AirLLM 2.8T LLM inference with single 4GB GPU

    Models