Menu
mutinai
What can I run?
Public preview · figures are illustrative fixture data, attributed to their source · data to May 2025 · read-only
Tool · Inference runtime · Ollama

Ollama

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

License
PermissiveMIT License
Language
Go
Latest release
15 Sept 2026Ollama v0.34.2
Measurements
0with this runtime
RepositoryWebsite

Relationships

Releases & news

  1. Ollama v0.34.2
    Added first-run setup when running ollama, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows.
  2. Ollama v0.34.1
    MLX safetensors ollama create no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization.
  3. Ollama v0.34.0
    Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS.
  4. Ollama v0.33.3
    gemma4 now supports images and audio on MLX engine
  5. Ollama v0.33.2
    Ollama's app now follows the system appearance again, restoring dark mode support
  6. Ollama v0.33.1
    MLX: Qwen3.8 Flash Next support
  7. Ollama v0.33.0
    Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
  8. Ollama v0.32.15
    New desktop onboarding flow on first launch
  9. Ollama v0.32.14
    llm: transcode WebP images for llama-server
  10. Ollama v0.32.13
    qwen3.8: support developer instructions
  11. Ollama v0.32.12
    This release adds the support of Qwen 3.8 27B. Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
  12. Ollama v0.32.11
    ollama launch dsh now supports DeepSeek Harness, DeepSeek's open-source agent harness
  13. Ollama v0.7.0
    New multimodal engine.

Measured performance with this runtime

Throughput members and projects recorded, in tokens per secondHow fast the model writes its answer; about 10 tokens per second reads like comfortable typing..

No performance measurements recorded yet.

Reviews

Contributions are not open yet, so there is nothing here from members.

Sources & history

Sources

  • GitHub (live source, 9 records, 19 Sept 2026)
  • GitHub (fixture) (illustrative fixture, 1 record, 13 Sept 2026)
  • Mutinai illustrative fixtures (illustrative fixture, 1 record, 13 Sept 2026)

External identifiers

Field history

  • homepageUrl = "https://ollama.com" — GitHub (current)
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub
  • homepageUrl = "https://ollama.com" — GitHub (fixture)
  • primaryLanguage = "Go" — GitHub (current)
  • primaryLanguage = "Go" — GitHub