Hundreds of models & providers. One command to find what runs on your hardware.
A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. Detects your hardware, scores each model across quality, speed, fit, and context dimensions, and tells you which ones will actually run well on your machine.
1.1.10 (2026-08-17)
Features
- mcp: add RamaLama runtime discovery (#875) (b9d5f57)
- models: add the Qwen3.8 family and fix Qwen generation parsing (#893) (6e024b2)
Bug Fixes
- bench: align 7900 XT hardwareName with the existing slug entries (c25754a)
- expose MiniMax M3 vision capability (#793) (4801d4a)
- ollama: stop one sized install marking a whole model family installed (#863) (c9a5678)
- providers: resolve MLX community tags to catalog ids (#854) (#860) (b79f2df)
What's Changed
- bench(apple-m4-pro): 32 MLX results — first MLX entries, head-to-head vs llama.cpp Metal on identical hardware by @Akciali in #853
- [Automated] Weekly benchmark cache refresh by @github-actions[bot] in #851
- [Automated] Weekly model data refresh by @github-actions[bot] in #852
- chore(deps): bump rmcp from 1.8.0 to 2.2.0 by @dependabot[bot] in #845
- chore(deps): bump actions/setup-node from 6.4.0 to 7.0.0 by @dependabot[bot] in #846
- chore: replace deprecated serde_yml dependency by @luojiyin1987 in #859
- fix(ollama): stop one sized install marking a whole model family installed by @AlexsJones in #863
- fix: expose MiniMax M3 vision capability by @octo-patch in #793
- docs: update AGENTS.md architecture and testing guidance by @luojiyin1987 in #857
- bench: community results for intel-alder-lake-p-gt2-iris-xe-graphics-integrated by @datawookie in #868
- bench: community results for radeon-840m-860m-graphics by @thelooter in #855
- bench: Muse-Glimmer-30B on amd-radeon-rx-7900-xt and apple-m4-pro by @Akciali in #870
- fix(providers): resolve MLX community tags to catalog ids by @Akciali in #860
- bench: community results for nvidia-geforce-gtx-1070 by @kopop2000 in #871
- chore(deps): bump async-nats from 0.49.1 to 0.50.0 by @dependabot[bot] in #849
- feat(models): add the Qwen3.8 family and fix Qwen generation parsing by @AlexsJones in #893
- [Automated] Weekly model data refresh by @github-actions[bot] in #892
- chore(deps): bump serde_json from 1.0.150 to 1.0.151 by @dependabot[bot] in #889
- feat(mcp): add RamaLama runtime discovery by @luojiyin1987 in #875
- bench: Qwen3.8-27B on amd-radeon-rx-7900-xt by @Akciali in #884
- chore(main): release 1.1.10 by @AlexsJones in #864
New Contributors
- @thelooter made their first contribution in #855
- @kopop2000 made their first contribution in #871
Full Changelog: v1.1.9...v1.1.10
| Publisher | AlexsJones |
|---|---|
| Version | 1.1.10 |
| Release date | 2026-08-17 |
| License | MIT |
| Installer type | zip |
| Architecture | x64 |
| Package ID | AlexsJones.llmfit |
winget install --id=AlexsJones.llmfit -ewinget upgrade --id=AlexsJones.llmfit -ewinget uninstall --id=AlexsJones.llmfit -ellmfit adds this command to the command line: llmfit.
Yes. llmfit is free and open-source software released under the MIT license.
The latest version is 1.1.10, released on Aug 17, 2026.
The download button links to the official installer published on github.com, the same file Windows Package Manager installs. You can verify the downloaded file by comparing its SHA-256 checksum with 86798cbbc44c91a818d10afc61b89f035fc961d62fe205d4c5a262611139b0dc.
llmfit runs on Windows and is available for 64-bit (x64) systems.
Open Settings › Apps › Installed apps, find llmfit and select Uninstall. From the command line, run winget uninstall --id=AlexsJones.llmfit -e.
Yes. llmfit is available as a portable ZIP archive (llmfit-v1.1.10-x86_64-pc-windows-msvc.zip, 64-bit (x64)) that runs without installation. Copy it to any folder or USB drive and run it from there.
Other AI for Productivity programs for Windows from different developers.
Private, local AI desktop app — run open LLMs fully offline with a coding agent, knowledge base and voice.
Ship 100x With The Agent IDE
Codex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.
Discover, download, and run local LLMs
An open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities.
Turn your computer into an AI computer