Pruna AI

Team

company

https://www.pruna.ai/

PrunaAI

PrunaAI

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

johnrachwanpruna updated a model about 9 hours ago

PrunaAI/Segmind-Vega-smashed

johnrachwanpruna updated a model about 9 hours ago

PrunaAI/test-save-tiny-stable-diffusion-pipe-smashed-pro

johnrachwanpruna updated a model about 9 hours ago

PrunaAI/test-save-tiny-random-llama3-smashed-pro

View all activity

Articles

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

PrunaAI 's models 10,409

PrunaAI/dphn-dolphin-2.1-mistral-7b-HQQ-4bit-smashed

Updated Jul 14 • 10

PrunaAI/dphn-dolphin-2_6-phi-2-HQQ-8bit-smashed

Updated Jul 14 • 10

PrunaAI/dphn-dolphin-2.1-mistral-7b-HQQ-8bit-smashed

Updated Jul 14 • 10

PrunaAI/dphn-dolphin-2.2.1-mistral-7b-HQQ-4bit-smashed

Updated Jul 14 • 17

PrunaAI/dphn-dolphin-2.9-llama3-8b-HQQ-4bit-smashed

Updated Jul 14 • 13

PrunaAI/dphn-dolphin-2.2.1-mistral-7b-HQQ-8bit-smashed

Updated Jul 14 • 10

PrunaAI/QuixiAI-Wizard-Vicuna-7B-Uncensored-HQQ-8bit-smashed

Updated Jul 14 • 9

PrunaAI/FLUX.1-schnell-smashed-no-compile

Text-to-Image • Updated Jul 9 • 4

PrunaAI/FLUX.1-schnell-smashed

Text-to-Image • Updated Jul 9 • 2 • 5

PrunaAI/FLUX.1-dev-smashed-no-compile

Text-to-Image • Updated Jul 9 • 7

PrunaAI/FLUX.1-dev-smashed

Text-to-Image • Updated Jul 9 • 25 • 5

PrunaAI/ibm-granite-granite-3.3-8b-instruct-HQQ-4bit-smashed

Updated Jul 9 • 9

PrunaAI/ibm-granite-granite-3.3-8b-instruct-HQQ-8bit-smashed

Updated Jul 9 • 11

PrunaAI/test-load-tiny-random-llama3-smashed-pro

Text Generation • 0.0B • Updated Jul 3 • 136

PrunaAI/HuggingFaceTB-SmolLM2-135M-HQQ-4bit-smashed

Updated Jul 1 • 11

PrunaAI/HuggingFaceTB-SmolLM2-135M-HQQ-8bit-smashed

Updated Jul 1 • 8

PrunaAI/test-load-tiny-random-llama4-smashed

Text Generation • 0.0B • Updated Jun 10 • 7

PrunaAI/test-load-tiny-stable-diffusion-pipe-smashed

Text-to-Image • Updated Jun 10 • 167

PrunaAI/test-load-tiny-stable-diffusion-pipe-smashed-pro

Text-to-Image • Updated Jun 10 • 127

PrunaAI/FLUX.1-Canny-dev-smashed

Text-to-Image • Updated Jun 10 • 2 • 2

PrunaAI/FLUX.1-Fill-dev-smashed

Updated Jun 10 • 2 • 2

PrunaAI/FLUX.1-Depth-dev-smashed

Text-to-Image • Updated Jun 10 • 1 • 1

PrunaAI/segolilylabs-Lily-Cybersecurity-7B-v0.2-HQQ-4bit-smashed

Updated Jun 5 • 9

PrunaAI/segolilylabs-Lily-Cybersecurity-7B-v0.2-HQQ-8bit-smashed

Updated Jun 5 • 7

PrunaAI/ALLaM-AI-ALLaM-7B-Instruct-preview-HQQ-4bit-smashed

Updated Jun 5 • 8

PrunaAI/facebook-KernelLLM-HQQ-8bit-smashed

Updated Jun 5 • 7

PrunaAI/facebook-KernelLLM-HQQ-4bit-smashed

Updated Jun 5 • 8

PrunaAI/nvidia-Llama-3.1-Nemotron-Nano-8B-v1-HQQ-8bit-smashed

Updated Jun 5 • 7

PrunaAI/JetBrains-Mellum-4b-base-HQQ-4bit-smashed

Updated Jun 5 • 8

PrunaAI/JetBrains-Mellum-4b-base-HQQ-8bit-smashed

Updated Jun 5 • 8