17t/s on a laptop with 6GB VRAM and DDR5 system memory. Maximum of 100k context window (then it saturates VRAM). Quite amazing, but tbh I'll still use inference providers, because it's too slow and it's my only machine with "good" specs :)

    cat docker-compose.yml
    services:
      llamacpp:
        volumes:
          - llamacpp:/root
        container_name: llamacpp
        restart: unless-stopped
        image: ghcr.io/ggml-org/llama.cpp:server-cuda
        network_mode: host
        command: |
          -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_XL --jinja --cpu-moe --n-gpu-layers 999 --ctx-size 102400 --temp 1.0 --top-p 0.95 --min-p 0.01 --top-k 40 --fit on
    # unsloth/gpt-oss-120b-GGUF:Q2_K
        deploy:
          resources:
            reservations:
              devices:
                - driver: nvidia
                  count: all
                  capabilities: [gpu]

    volumes:
       llamacpp: