How-toUpdated 2026-07-01 · 9 min read · by RTXsparks Lab
Serving Llama 3.2 90B Vision with Ollama on RTX Spark
Production Ollama deployment of Llama 3.2 90B Vision on RTX Spark. Configs, systemd, TLS, observability.
Install
Install Ollama via pip/docker/apt as appropriate. Verify GPU visibility with nvidia-smi.
- # Ollama install
- curl -fsSL https://ollama.com/install.sh | sh
Config
Optimized Ollama config for Llama 3.2 90B Vision at Q4_K_S: batch, KV cache dtype, and parallelism knobs.
Systemd unit
[Unit] Description=Ollama for Llama 3.2 90B Vision — [Service] ExecStart=/usr/bin/ollama serve llama-3-2-90b-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 Ollama port.
Observability
Scrape Ollama Prometheus metrics into Grafana; watch tokens_per_second, batch_size, and kv_cache_usage.
Frequently asked questions
Is Ollama the fastest for Llama 3.2 90B Vision?
It's the easiest, not always the fastest.
Can I run multiple models with one instance?
Yes, it hot-swaps.