The Ollama Commands You Will Use Every Day

Laptop showing a terminal window

Ollama has a long command list, but day to day you will use a handful of them. They cover the whole loop: download a model, run it, check where it landed in memory, unload it, and clean up the disk. Every command below comes from Ollama's own CLI reference and FAQ.

Get a model and run it

ollama pull qwen3:8b downloads a model without starting it, which is handy when you want a large download done before you sit down to work. ollama run qwen3:8b starts a chat with it in the terminal. You can also put a prompt in quotes after the model name, which turns run into a one-shot command you can call from a script.

See what is loaded

ollama ps lists running models, and the column to read is PROCESSOR. Ollama's FAQ says 100% GPU means the model loaded entirely into the GPU, 100% CPU means it loaded entirely into system memory, and a split such as 48%/52% CPU/GPU means it sits partly in each. A split is the most common reason a local model suddenly feels slow, and it usually means the model, the context window, or both are too big for your card.

ollama stop qwen3:8b unloads a model right away. By default, the FAQ says, Ollama keeps a model in memory for 5 minutes after you finish so the next request starts faster. Stopping it frees that VRAM immediately, which helps before you load something bigger.

Keep the disk tidy

ollama ls lists every model on disk, and ollama rm qwen3:8b deletes one. Model files add up quickly. Ollama's library lists the qwen3:32b download at 20 GB, so a weekend of trying different sizes and quants can fill a small SSD.

Make a model your own

ollama create mymodel -f Modelfile builds a custom model from a short text file. A Modelfile can set a system message and parameters such as num_ctx, the context window size. That is a clean way to give one model a bigger window without changing the default for everything else.

Two settings worth knowing

The FAQ says Ollama uses a 4096-token context window by default. To raise it for every model, set OLLAMA_CONTEXT_LENGTH before the server starts, for example to 8192. A bigger window costs memory, so check ollama ps again after you change it.

The second is OLLAMA_KV_CACHE_TYPE, which controls the precision of the KV cache, the memory that holds the conversation so far. The default is f16. Per the FAQ, q8_0 uses about half the memory of f16 with a very small loss in precision, and q4_0 uses about a quarter with a larger loss that can show up at long context sizes. Cache quantization needs flash attention; Ollama turns it on automatically where the backend supports it, and OLLAMA_FLASH_ATTENTION=1 forces it on. Both cache settings are global, so they apply to every model the server loads.

If you start the server by hand with ollama serve, that is where these environment variables go.

The Ollama cheat sheet on llmhardware.io has the full list, including the REST API and more environment variables.

Sources: Ollama CLI reference (docs.ollama.com/cli), Ollama FAQ (docs.ollama.com/faq), Modelfile reference (docs.ollama.com/modelfile), Ollama model library.

Comments

Post a Comment

Popular posts from this blog

AMD RX 9070 XT for Local LLMs: ROCm Performance Guide (2026)

The AMD RX 9070 XT launched in early 2026 at $599 with 16GB GDDR6 and 648 GB/s memory bandwidth. For local LLM users who want a mid-range GPU without NVIDIA prices, this changes the calculus significantly. Here is what it actually delivers. RX 9070 XT Specs vs Competition GPU VRAM Bandwidth Price LLM Score RX 9070 XT 16 GB 648 GB/s $599 ~60 tok/s RTX 4070 Ti Super 16 GB 672 GB/s $799 ~62 tok/s RTX 4080 Super 16 GB 736 GB/s $999 ~68 tok/s RTX 4090 24 GB 1,008 GB/s ~$1,100 ~90 tok/s At $599 with 16GB VRAM, the RX 9070 XT is the best value GPU for local LLMs in the mid-range tier in 2026. See the full comparison at LLMHardware.io's AMD GPU guide . ROCm Setup on Linux (2026) # Ubuntu 22.04/24.04 sudo apt install rocm-hip-libraries hip-base # or use the AMD installer: wget https://repo.radeon.com/amdgpu-install/6.3/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb sudo dpkg -i amdgpu-install*.deb sudo amdgpu-install --usecase=rocm,lrt,openclsdk # Verify ROCm sees your GPU r...
Read more

llama.cpp flash attention: how to enable and benchmark

Image
Flash attention computes attention with far less memory traffic. The math is identical; the memory movement is not. In llama.cpp it matters most in two situations: long context windows and tight video memory (VRAM). With flash attention enabled, the key-value cache shrinks substantially. A 32k-token context window becomes realistic on a 16GB card, and the prompt-processing phase speeds up, so long documents get ingested faster. The catch is compatibility: not every model and quantization combination supports it, and on some setups the speedup is modest. If you run short chats on a strong GPU, you may barely notice. Where it shines is retrieval-augmented generation (RAG) and long-document work on mid-range cards. Enable it, compare your tokens per second, and keep it if your workload benefits. For the common case of pasting a long PDF and asking questions, it is close to free performance. See how context length changes VRAM needs .
Read more

SillyTavern with Local LLMs: Complete Setup for AI Companions

Image
SillyTavern is the most feature-rich frontend for character-based AI conversations. What began as an AI roleplay tool has evolved into a powerful platform with persona management, memory systems, extensive prompt engineering tools, and connections to every major local inference backend. Here's how to set it up with local models. Quick connect: SillyTavern connects to Ollama, KoboldCpp, llama.cpp server, and TabbyAPI (ExLlamaV2) out of the box. Any of the hardware setups at LLMHardware.io provides a solid backend for SillyTavern. Installation Install via git: git clone https://github.com/SillyTavern/SillyTavern && cd SillyTavern && npm install then node server.js . Access at localhost:8000. For persistent installation, use the included start.sh script. SillyTavern uses Node.js and runs on any platform. The companion app (STMP) enables mobile access to your SillyTavern instance via Tailscale or local network. Character Cards and the TavernAI Format Chara...
Read more