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 4 hours ago

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

johnrachwanpruna updated a model about 4 hours ago

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

sharpenb published a model about 16 hours ago

PrunaAI/NexaAI-Octopus-v2-HQQ-4bit-smashed

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 10,399

PrunaAI/openai-community-gpt2-bnb-8bit-smashed

Text Generation • 0.1B • Updated Apr 4 • 16

PrunaAI/tiiuae-falcon-7b-HQQ-4bit-smashed

Updated Apr 4 • 3

PrunaAI/tiiuae-falcon-7b-bnb-4bit-smashed

Text Generation • 4B • Updated Apr 4 • 9

PrunaAI/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B-HQQ-4bit-smashed

Updated Apr 4 • 5

PrunaAI/microsoft-phi-1_5-HQQ-4bit-smashed

Text Generation • Updated Apr 4 • 7

PrunaAI/microsoft-Phi-3.5-mini-instruct-bnb-4bit-smashed

2B • Updated Apr 4 • 4

PrunaAI/microsoft-phi-1_5-HQQ-8bit-smashed

Updated Apr 4 • 3

PrunaAI/microsoft-Phi-3-mini-4k-instruct-HQQ-4bit-smashed

Text Generation • Updated Apr 4 • 10

PrunaAI/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B-HQQ-8bit-smashed

Updated Apr 4 • 4

PrunaAI/microsoft-Phi-3.5-mini-instruct-bnb-8bit-smashed

4B • Updated Apr 4 • 4

PrunaAI/microsoft-Phi-3-mini-4k-instruct-HQQ-8bit-smashed

Updated Apr 4 • 3

PrunaAI/microsoft-phi-1_5-bnb-4bit-smashed

Text Generation • 0.8B • Updated Apr 4 • 36

PrunaAI/teknium-OpenHermes-2.5-Mistral-7B-bnb-4bit-smashed

Text Generation • 4B • Updated Apr 4 • 10

PrunaAI/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B-bnb-4bit-smashed

1B • Updated Apr 4 • 4

PrunaAI/microsoft-phi-1_5-bnb-8bit-smashed

Text Generation • 1B • Updated Apr 4 • 8

PrunaAI/deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B-bnb-8bit-smashed

2B • Updated Apr 4 • 4

PrunaAI/TinyLlama-TinyLlama-1.1B-Chat-v1.0-HQQ-4bit-smashed

Updated Apr 4 • 5

PrunaAI/microsoft-Phi-3-mini-4k-instruct-bnb-4bit-smashed

Text Generation • 2B • Updated Apr 4 • 8

PrunaAI/meta-llama-Llama-2-7b-hf-HQQ-4bit-smashed

Updated Apr 4 • 3

PrunaAI/TinyLlama-TinyLlama-1.1B-Chat-v1.0-HQQ-8bit-smashed

Updated Apr 4 • 4

PrunaAI/google-gemma-2-2b-it-HQQ-8bit-smashed

Updated Apr 4 • 4

PrunaAI/microsoft-phi-2-bnb-8bit-smashed

3B • Updated Apr 4 • 3

PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-8bit-smashed

Updated Apr 4 • 3

PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed

Text Generation • Updated Apr 4 • 10

PrunaAI/meta-llama-Llama-2-7b-hf-HQQ-8bit-smashed

Updated Apr 4 • 3

PrunaAI/microsoft-Phi-3-mini-128k-instruct-bnb-4bit-smashed

Text Generation • 2B • Updated Apr 4 • 8

PrunaAI/NousResearch-Yarn-Mistral-7b-128k-HQQ-8bit-smashed

Updated Apr 4 • 4

PrunaAI/NousResearch-Yarn-Mistral-7b-128k-HQQ-4bit-smashed

Updated Apr 4 • 3

PrunaAI/google-gemma-2-2b-bnb-8bit-smashed

3B • Updated Apr 4 • 4

PrunaAI/NousResearch-Yarn-Mistral-7b-128k-bnb-4bit-smashed

Text Generation • 4B • Updated Apr 4 • 6