RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Learn
  4. /How-to
  5. /How to delete unused models to free up disk space
HOW-TO · INF

How to delete unused models to free up disk space

beginner·5 min·By Fredoline Eruo
Target environment
Ubuntu 24.04 · Ollama 0.4.x
PREREQUISITES

Ollama installed, at least one model downloaded

What this does

Removes one or more downloaded model files from the local Ollama store, reclaiming the occupied disk space. The model must be specified by its exact name and will be unavailable for subsequent ollama run calls until re-pulled.

Steps

  1. Inspect current disk usage. Produces a baseline of used and available space.

    df -h ~/.ollama/models
    

    Expected output: A filesystem row showing used and available blocks for the model directory mount.

  2. List models with their sizes. Identifies targets for deletion.

    ollama list
    

    Expected output: Table where the SIZE column lists each model's byte footprint.

  3. Delete the target model. Removes all blobs and manifest entries for the named model.

    ollama rm llama3.2
    

    Expected output: No output on success; the shell prompt returns immediately.

  4. Confirm space returned. Verifies the deletion succeeded and the filesystem volume reflects the freed space.

    df -h ~/.ollama/models && ollama list
    

    Expected output a): filesystem row shows a smaller used value; Expected output b): the deleted model no longer appears in the list.

Verification

ollama list
# Expected: the previously listed model row is absent from the NAME column

Common failures

  • model 'xxx' not found - Typo or case mismatch; check the exact name from ollama list.
  • cannot remove model 'xxx': no such file - Model already deleted or path was manually altered.
  • permission denied - Insufficient filesystem permissions on ~/.ollama/models; use elevation if required.
  • wrong model removed - Name collision; always double-check the exact string before passing to rm.
  • Error: server error - Daemon interrupted; restart with ollama serve and retry.

Operator checkpoint

Before treating this as solved, write down the local runtime, model or package version, hardware/backend if relevant, and the verification output. This keeps the guide useful as a Will-It-Run style decision instead of a one-off command transcript.

Related guides

  • How to pull and run your first open-source LLM using Ollama
  • How to list all available models on your local Ollama installation
RELATED GUIDES
INF
How to pull and run your first open-source LLM using Ollama
INF
How to list all available models on your local Ollama installation
← All how-to guidesCourses →