Classify images on a VPS with Ollama's Clef
Run Cloudflare's Clef vision decision models in Ollama on your VPS. Moderate uploads and route tickets with screenshots, and the image never leaves the box.
#ollama
Filtering by topic #ollama · clear
Air-gapped AI server: what it takes
An air gap means no network path at all, and a rented VPS cannot give you one. Build egress-denied inference instead: default-deny outbound, staged weights.
Triage support tickets with Ollama on a VPS
Classify support tickets on your own VPS with an Ollama decision model: one /v1/systemone call answers every question at once, no API key.
Run Ollama cloud models from a small VPS
Ollama on a small no-GPU VPS with cloud models doing the inference: signin without a browser, a private API on 11434, quotas, and a local fallback.
Ollama KV cache quantization: q8_0 vs f16
Raised num_ctx and Ollama no longer fits? The KV cache grew, not the weights. Set OLLAMA_KV_CACHE_TYPE with flash attention and watch the change in ollama ps.
Run Meta Muse Glimmer 30B on a VPS
Muse Glimmer's Linux tags run from 18GB to 59GB. Work out the RAM and disk a rented VPS needs before you pull, and what CPU only inference costs.
Run EmbeddingGemma 2 on a CPU-only VPS
Ollama 0.40 cannot run EmbeddingGemma 2 on a Linux CPU yet. Here is the sentence-transformers setup that does, with task prefixes and 256d vectors in pgvector.
Ollama pull vs run, and where models live
ollama pull downloads a model and stops. ollama run downloads it, then opens a chat. Where the files land, why they fill a VPS root disk, how to move them.
Ollama num_predict: cap the output length
num_predict caps how many tokens Ollama will write. The three places to set it, which one wins, and how to read done_reason in the response.
Host Ollama on a VPS: self-host an LLM safely
A 7B model wants 8 GB of RAM and gives 4 to 10 tokens per second on CPU. Host one on a VPS and call it at 127.0.0.1:11434/v1, with port 11434 kept closed.
Use Ollama with your coding agent
Point a coding agent at a model you host: the base URL, the dummy key, the context length that breaks everything, and the jobs a local model wins.
Self-host mem0 for agent memory on a VPS
Run the mem0 memory server on your own VPS: the real RAM floor, a Compose file that binds to localhost, TLS in front of the API, and a fully local Ollama path.
Your Ollama API has no password
The Ollama server ships with no authentication, so anything that reaches port 11434 can run your models and pull new ones. The three fixes, in order.
Reasoning effort settings on a local LLM
Reasoning effort sets how long a local model thinks before it answers. What the levels change on your own hardware, and how to measure the real cost.
Can you self-host Claude? The honest answer
Claude's weights are not public, so no server of yours can run it. Here is what you can self-host instead: open models, a gateway, and Claude Code.
Configure dsh: API keys, models, endpoints
Where dsh keeps its config on Linux, how to wire a DeepSeek API key or a local Ollama endpoint, and exactly what leaves your box in each mode.
Run Nemotron 3.5 Lightning on a VPS
Run NVIDIA Nemotron 3.5 Lightning with Ollama on your own server: the exact tag to pull, how much RAM it needs, and if CPU-only is fast enough.
Run GLM 5.2 on a VPS with Ollama
GLM 5.2 is cloud only in Ollama's library. Here is the GLM model that actually fits a VPS, and the RAM each quantisation needs on your own box.
Ollama temperature and sampling settings
Temperature does not make a model smarter. Here is what it does to the token distribution in Ollama, plus top_p, top_k, min_p, seed, and which place wins.
Ollama concurrency: NUM_PARALLEL and MAX_QUEUE
The second request waits, or it is refused: what OLLAMA_NUM_PARALLEL and OLLAMA_MAX_QUEUE really control, and why every parallel slot costs you memory.
Ollama Cloud vs your own server: what changes
Ollama Cloud and a self-hosted Ollama share one CLI and one API. See exactly which settings change, and what leaves your machine on each path.
Zanus AI server: quote-only vs building your own
Zanus AI's no-code AI server is sold by quote only. What the same private stack takes to build on a rented GPU server, and when an API is the better buy.
Run a coding AI agent on a VPS
Run Aider or Goose on a VPS to code from your terminal, connected to a hosted or a self-hosted Ollama model. Setup, model sizing, and safety.
Open WebUI alternatives for a VPS
Open WebUI, LibreChat, Hollama and OrionChat compared on a VPS with a public IP: RAM left for the model, logins, remote Ollama, and upkeep.
Ollama vs vLLM: which LLM server to run
Ollama is a convenience layer for one user, on CPU if needed. vLLM is a throughput engine for GPUs. Pick by workload, with the real commands for both.
Ollama vs llama.cpp on a VPS
llama.cpp is the engine, Ollama is the layer on top. Which one to run on a CPU-only VPS, how quantisation choice changes RAM, and when neither fits.
Which AI models can you self-host?
Pick a model by the RAM you actually have. Sizing arithmetic for 4 GB, 16 GB and 64 GB VPS plans, honest CPU token rates, and the hidden cost of context.
Self-host Octop: a multi-user AI assistant
Deploy Octop on a VPS with Docker Compose pinned to a tag: per-user isolation, an OpenAI-compatible model backend, TLS, and why to skip the curl installer.
Ollama quantization: Q4 vs Q8 vs fp16
Pick an Ollama quantization with arithmetic instead of guesswork: what q4_K_M, q8_0 and fp16 cost in RAM, and where the quality actually drops.
Why your self-hosted LLM stalls at 5 users
One user was fine, five crawl. How batching, KV cache limits, prefill and queue depth decide how many people your LLM server can serve at once.
Run Qwen 3.8 27B on a VPS With Ollama
Qwen 3.8 27B is now on Ollama as qwen3.8:27b. Here is the RAM and speed arithmetic for running it on a CPU-only VPS, and what fits in 8 to 64 GB.
Keep an Ollama model loaded in memory
Ollama unloads a model after 5 minutes idle, so the next request waits for a reload. Set keep_alive in a systemd override so it survives reboots, then preload.
Import a GGUF model into Ollama
Run a .gguf from Hugging Face or from a local file under Ollama, and fix the chat template mismatch that makes an imported model reply in garbage.
Ollama context length: set num_ctx and size RAM
Ollama truncates long prompts at a small default context. Set num_ctx per request or OLLAMA_CONTEXT_LENGTH server-wide; size KV cache RAM before raising it.
Measure tokens per second on a local LLM
A rented GPU only beats per-token billing above a throughput floor. Measure tokens per second properly with a concurrency sweep, then decide.
Ollama: fix context deadline exceeded
Ollama context deadline exceeded means a timeout fired before the model answered. Find which layer set it: your client, the model load, or nginx.
Run Ollama in rootless Podman on a VPS
Run Ollama as a rootless Podman container on a VPS: a dedicated user, lingering, a Quadlet unit that survives reboot, SELinux labels, and a closed port.
Can Ollama Search the Web? Three Ways to Do It
Ollama does not browse on its own. Give a local model search through Ollama's web search API, Open WebUI with SearXNG, or a short Python tool loop you control.
Run Laya on a VPS: pip, Ollaya or Ollama?
Self-host the Laya decision model on a CPU VPS with laya-serve 0.3.26, keep it off the public internet, and learn why Ollama cannot load it but Ollaya can.
Is Ollama free? Local use vs Ollama Cloud
Ollama is MIT licensed and free to run on hardware you own. What costs money is Ollama Cloud and the machine with enough RAM to hold the model.
Run Gemma 4 on a VPS: sizing and speed
Which Gemma 4 tag fits your VPS RAM, what each one costs in tokens per second on CPU, and the sizing arithmetic to check it before you pull 20GB.
The Ollama API and port 11434 explained
Curl your Ollama server on port 11434, read what a refused connection means, tour the API endpoints, and set OLLAMA_HOST without exposing the box.
Run DeepSeek V4 Flash on a VPS
DeepSeek V4 Flash on Ollama is cloud only. Get the real disk and RAM numbers for every GGUF build, and see which VPS plan can actually load it.