LLM Torrents
Models Collections Learn Hardware Log in

Learn

Plain-language explainers for running open-weight models locally.

  • Quantization formats explained

    GGUF, AWQ, GPTQ, EXL2 and MLX — what they are, and what Q4_K_M means.

  • VRAM guide: what fits in 8, 12, 16 and 24 GB

    How model size, quantization and context add up to a memory budget.

  • Context and the KV cache

    Why a longer context costs memory, and what KV-cache quantization trades.