# PrunaAI/pruna

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

Repository: https://github.com/PrunaAI/pruna
Canonical: https://ross.abutalabs.com/products/pruna
Homepage: https://docs.pruna.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, computer-vision, deep-learning, llm, machine-learning, optimization, python, speech-recognition, diffusion-models, diffusers, transformers, hacktoberfest
Last push: 2026-09-02T21:54:03+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 89, longevity 38
- inputs: {"age_days": 540, "days_push": 0, "days_rel": 72, "gap_med": 19.0, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1275, forks 102 (observed 2026-09-03T02:15:07.108233+00:00)

## What it is
Pruna is an open-source Python model optimization framework that makes AI models faster, smaller, cheaper, and greener via caching, quantization, pruning, distillation, and compilation techniques. It works with popular model stacks like transformers and diffusers and is maintained by Pruna AI, which also offers hosted performance-model endpoints.

## Use cases
- speed up inference of my huggingface model
- quantize a diffusion model to reduce memory
- compress an LLM with pruning and distillation
- make my text-to-image model generate faster
- reduce GPU cost for model serving
- benchmark model speed and quality after optimization
- shrink a speech recognition model for deployment

## When to choose
- you want a unified API to apply multiple compression techniques (quantization, caching, pruning, distillation, compilation) to transformers or diffusers models
- you need to trade off speed, size, cost, and quality for inference in Python on GPU
- you want to optimize open-source models yourself rather than use a hosted API

## When to avoid
- you need training-time optimization or fine-tuning acceleration rather than inference compression
- you want a fully managed inference API without managing models yourself (consider Pruna's hosted endpoints instead)
- your model is not based on a supported stack like transformers or diffusers

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, image-processing, speech-recognition, benchmarking
- domain: machine-learning, deep-learning, large-language-models, computer-vision, image-processing, performance
- platform: python, cross-platform
- tags: model-optimization, quantization, pruning, distillation, model-compression, inference-acceleration, diffusion-models, transformers, huggingface, gpu, linux

## Member repositories
- PrunaAI/pruna (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:07.108233+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 2026-08-30T05:03:15.167220+00:00, confidence not recorded.
  - readme: https://github.com/PrunaAI/pruna (fetched 2026-09-03T02:15:07.108233+00:00, sha 9758bfe3f325)
  - homepage: https://docs.pruna.ai (fetched 2026-08-29T12:14:52.019135+00:00, sha ec07fd84fc95)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/index.html (fetched 2026-08-29T12:14:52.022358+00:00, sha f3444d9e1641)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-image-ideogram.html (fetched 2026-08-29T12:14:52.025930+00:00, sha 6a6e0c5f8cb3)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-image.html (fetched 2026-08-29T12:14:52.028688+00:00, sha 104fc2be1d2c)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-image-edit.html (fetched 2026-08-29T12:14:52.030961+00:00, sha 3a64cbe3cf10)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-image-try-on.html (fetched 2026-08-29T12:14:52.033271+00:00, sha f7387418e115)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-image-upscale.html (fetched 2026-08-29T12:14:52.035729+00:00, sha 47d21f95fd15)
  - site_page: https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video.html (fetched 2026-08-29T12:14:52.038984+00:00, sha 1ea70774290a)
- Data as of 2026-08-30T08:39:29.467469+00:00.