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

davidberenstein1957 published a model about 1 hour ago

PrunaAI/test-tiny-clip-t5-model

johnrachwanpruna updated a model about 7 hours ago

PrunaAI/Segmind-Vega-smashed

sharpenb published a model 1 day ago

PrunaAI/Chain-GPT-Solidity-LLM-HQQ-8bit-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 10,402

PrunaAI/facebook-galactica-6.7b-HQQ-4bit-smashed

Updated Jun 5 • 1

PrunaAI/fdtn-ai-Foundation-Sec-8B-bnb-4bit-smashed

5B • Updated Jun 5 • 3

PrunaAI/facebook-galactica-6.7b-HQQ-8bit-smashed

Updated Jun 5 • 4

PrunaAI/cognitivecomputations-Wizard-Vicuna-7B-Uncensored-HQQ-4bit-smashed

Updated Jun 4 • 1

PrunaAI/ALLaM-AI-ALLaM-7B-Instruct-preview-HQQ-8bit-smashed

Updated Jun 4 • 3

PrunaAI/ByteDance-Seed-Seed-Coder-8B-Reasoning-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/ByteDance-Seed-Seed-Coder-8B-Reasoning-HQQ-4bit-smashed

Updated Jun 4 • 2

PrunaAI/open-r1-OlympicCoder-7B-HQQ-4bit-smashed

Updated Jun 4 • 2

PrunaAI/open-r1-OlympicCoder-7B-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/CohereLabs-c4ai-command-r7b-arabic-02-2025-HQQ-4bit-smashed

Updated Jun 4 • 6

PrunaAI/CohereLabs-c4ai-command-r7b-arabic-02-2025-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/motherduckdb-DuckDB-NSQL-7B-v0.1-HQQ-8bit-smashed

Updated Jun 4 • 2

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

Updated Jun 4 • 3

PrunaAI/deepseek-ai-deepseek-llm-7b-base-HQQ-4bit-smashed

Updated Jun 4 • 1

PrunaAI/Qwen-Qwen2.5-1.5B-HQQ-4bit-smashed

Updated Jun 4 • 4

PrunaAI/Qwen-Qwen2.5-1.5B-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/nvidia-Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-HQQ-4bit-smashed

Updated Jun 4 • 3

PrunaAI/nvidia-Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/fdtn-ai-Foundation-Sec-8B-bnb-8bit-smashed

8B • Updated Jun 4 • 16

PrunaAI/Qwen-Qwen2.5-Coder-7B-HQQ-4bit-smashed

Updated Jun 4 • 2

PrunaAI/Qwen-Qwen2.5-Coder-7B-HQQ-8bit-smashed

Updated Jun 4 • 2

PrunaAI/fdtn-ai-Foundation-Sec-8B-HQQ-4bit-smashed

Updated Jun 4 • 4

PrunaAI/fdtn-ai-Foundation-Sec-8B-HQQ-8bit-smashed

Updated Jun 4 • 4

PrunaAI/Llama-3.2-1b-Instruct-smashed

Text Generation • 1B • Updated Jun 3 • 7 • • 1

PrunaAI/segmind-tiny-sd-smashed

Text-to-Image • Updated Jun 3 • 2

PrunaAI/Llama-3.1-8b-Instruct-4bit-bnb

Text Generation • 5B • Updated Jun 3 • 1

PrunaAI/tiny-stable-diffusion-pipe-smashed

Text-to-Image • Updated May 15 • 2

PrunaAI/tiny-random-llama4-smashed

Text Generation • 0.0B • Updated May 7 • 3

PrunaAI/baichuan-inc-Baichuan-7B-HQQ-4bit-smashed

Updated Apr 4 • 5

PrunaAI/microsoft-phi-2-bnb-4bit-smashed

Text Generation • 2B • Updated Apr 4 • 4