Pruna AI

company

https://www.pruna.ai/

Activity Feed Request to join this org

AI & ML interests

Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.

Recent Activity

sharpenb published a model about 2 hours ago

PrunaAI/project-numina-NuminaMath-7B-TIR-HQQ-8bit-smashed

sharpenb updated a model about 2 hours ago

PrunaAI/project-numina-NuminaMath-7B-TIR-HQQ-8bit-smashed

sharpenb published a model about 2 hours ago

PrunaAI/project-numina-NuminaMath-7B-TIR-HQQ-4bit-smashed

View all activity

Articles

Pruna 0.3.2: More OSS Algos, More Ways to Optimize

LLM Architectures Explained: What Powers Today’s Top Models

Slashing torch.compile Warmup & LoRA Swapping Times with Pruna

SmolLM-Smashed: Tiny Giants, Optimized for Speed

AI Model Optimization More Flexible Than Ever

Effective Prompting for Generative Vision Models

Measuring What Matters: Objective Metrics for Image Generation Assessment

Faster ComfyUI Nodes for Flux and Stable Diffusion with Pruna

🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6 times faster)!

An Introduction to AI Model Optimization Techniques

Optimise AI Models and Make Them Faster, Smaller, Cheaper, Greener

View all articles

PrunaAI 's Spaces 4

P-Bench

A cost/quality/speed Leaderboard for Inference Providers!

Frame Arena

Frame by frame video comparison tool with quality metrics

P-Q-Image-2.1

Few-step LoRA for Qwen-Image-2.1 (6-steps v0.2)

README