atlasium-efficient/Llama-3.1-5B-40pct-Compressed-8B-EN-V1
Text Generation • 5B • Updated • 23
Compressed Models V1
Compressed LLMs (Qwen3, Llama families). V1 (First Version)
-
-
atlasium-efficient/Llama-3.1-6B-25pct-Compressed-8B-EN-V1
Text Generation • 6B • Updated • 22 -
atlasium-efficient/Llama-3.1-6B-30pct-Compressed-8B-EN-V1
Text Generation • 6B • Updated • 25 -
atlasium-efficient/Llama-3.1-6B-35pct-Compressed-8B-EN-V1
Text Generation • 6B • Updated • 17 -
atlasium-efficient/Llama-3.1-7B-20pct-Compressed-8B-EN-V1
Text Generation • 7B • Updated • 26 -
atlasium-efficient/Llama-3.2-2B-30pct-Compressed-3B-EN-V1
Text Generation • 2B • Updated • 21 -
atlasium-efficient/Llama-3.2-2B-35pct-Compressed-3B-EN-V1
Text Generation • 2B • Updated • 20 -
atlasium-efficient/Llama-3.2-2B-40pct-Compressed-3B-EN-V1
Text Generation • 2B • Updated • 26 -
atlasium-efficient/Llama-3.2-3B-20pct-Compressed-3B-EN-V1
Text Generation • 3B • Updated • 24 -
atlasium-efficient/Llama-3.2-3B-25pct-Compressed-3B-EN-V1
Text Generation • 3B • Updated • 24 -
atlasium-efficient/Qwen3-11B-25pct-Compressed-14B-EN-V1
Text Generation • 11B • Updated • 73 -
atlasium-efficient/Qwen3-11B-30pct-Compressed-14B-EN-V1
Text Generation • 11B • Updated • 96 -
atlasium-efficient/Qwen3-12B-20pct-Compressed-14B-EN-V1
Text Generation • 12B • Updated • 115 -
atlasium-efficient/Qwen3-3B-20pct-Compressed-4B-EN-V1
Text Generation • 3B • Updated • 50 -
atlasium-efficient/Qwen3-3B-25pct-Compressed-4B-EN-V1
Text Generation • 3B • Updated • 54 -
atlasium-efficient/Qwen3-3B-30pct-Compressed-4B-EN-V1
Text Generation • 3B • Updated • 56