# AlexsJones/llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

Repository: https://github.com/AlexsJones/llmfit
Canonical: https://ross.abutalabs.com/products/llmfit
Language: Rust
License: MIT
License Family: permissive
Topics: llm, skill, localai, gguf, mlx, unsloth
Last push: 2026-08-25T12:39:19+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 14
- inputs: {"age_days": 199, "days_push": 8, "days_rel": 8, "gap_med": 0.0, "n_releases_24m": 129}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 34236, forks 2139 (observed 2026-08-28T04:11:58.719179+00:00)

## What it is
llmfit is a Rust-based terminal tool (TUI and CLI) that matches LLM models to your hardware by detecting RAM, CPU, and GPU and scoring models on quality, speed, fit, and context. It supports hundreds of models and providers, multi-GPU setups, MoE architectures, quantization selection, speed estimation, and community benchmark contributions.

## Use cases
- find which LLM models run on my hardware
- check if a GGUF model fits in my RAM
- recommend local LLM for my GPU
- estimate tokens per second for a model on my machine
- compare model quality vs speed for local inference
- pick the right quantization for my VRAM

## When to choose
- you run local LLMs with Ollama, llama.cpp, MLX, or LM Studio and want to know what fits
- you want hardware-aware model recommendations with speed and quality scoring
- you prefer an interactive TUI plus scriptable CLI in one tool

## When to avoid
- you need to actually serve or chat with models rather than select them
- you only use cloud APIs and never run models locally
- you need GPU cluster-scale inference scheduling

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, benchmarking, cli, terminal-ui, developer-tools
- domain: large-language-models, developer-tools, machine-learning
- platform: windows, cli, rust
- tags: gguf, local-llm, hardware-detection, model-selection, tui, ollama, llama-cpp, mlx, command-line, linux, macos

## Member repositories
- AlexsJones/llmfit (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:58.719179+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:27:43.553709+00:00, confidence not recorded.
  - readme: https://github.com/AlexsJones/llmfit (fetched 2026-08-28T04:11:58.719179+00:00, sha adb7ca38b9a6)
  - registry_crates: https://crates.io/api/v1/crates/llmfit (fetched 2026-08-29T07:48:18.042988+00:00, sha 138b92b6535b)
- Data as of 2026-08-30T08:39:29.467469+00:00.