How-toUpdated 2026-07-01 · 9 min read · by RTXsparks Lab

Serving Llama 3.2 11B Vision with llama.cpp on RTX Spark

Production llama.cpp deployment of Llama 3.2 11B Vision on RTX Spark. Configs, systemd, TLS, observability.

Install

Install llama.cpp via pip/docker/apt as appropriate. Verify GPU visibility with nvidia-smi.

  • # llama.cpp install
  • brew install llama.cpp

Config

Optimized llama.cpp config for Llama 3.2 11B Vision at Q5_K_M: batch, KV cache dtype, and parallelism knobs.

Systemd unit

[Unit] Description=llama.cpp for Llama 3.2 11B Vision — [Service] ExecStart=/usr/bin/llama-cpp serve llama-3-2-11b-vision --port 8000 — Restart=always.

nginx + TLS

Terminate TLS at nginx with a Let's Encrypt cert, rate-limit at 20 req/s per IP, and proxy to the local llama.cpp port.

Observability

Scrape llama.cpp Prometheus metrics into Grafana; watch tokens_per_second, batch_size, and kv_cache_usage.

Frequently asked questions

Is llama.cpp the fastest for Llama 3.2 11B Vision?

It's the easiest, not always the fastest.

Can I run multiple models with one instance?

One process per model is standard.

Related guides