List your company

Accuracy on LLaMA2-7B zero-shot evaluation suite

67.18Zero-Shot AccuracyQTIP
30.93640.345549.75559.1645Dec 15, 2025Dec 23, 2025Jan 1, 2026Jan 10, 2026Jan 19, 2026Jan 28, 2026Feb 6, 2026

Evaluation results

MethodLinks
QTIPVariant=2-bit, Model Size=2.15 GB, Data=12.58M2026.0267.18————————
AQLM + PVVariant=2-bit-1x16, Model Size=2.38 GB, Data=8.00M2026.0264.04————————
AQLM + PVVariant=2-bit-2x8, Model Size=2.15 GB, Data=8.00M2026.0263.68————————
AQLMVariant=2-bit-1x16, Model Size=2.38 GB, Data=8.00M2026.0263.46————————
AQLMVariant=2-bit-2x8, Model Size=2.15 GB, Data=8.00M2026.0259.53————————
NANOQUANTVariant=2-bit, Model Size=1.68 GB, Data=1.05M2026.0256.9————————
DenseComp. Rate=0%, Base Model=LLaMA2-7B, Fine-tuning=None2025.1254.79————————
SkipCatComp. Rate=20%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1254.41———————0.39
SVD-LLMComp. Rate=20%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1251.02———————3.78
NANOQUANTVariant=1-bit, Model Size=1.24 GB, Data=1.05M2026.0251.01————————
SkipCatComp. Rate=40%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1248.65———————6.15
SVD-LLMComp. Rate=40%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1246.91———————7.88
SkipCatComp. Rate=60%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1241.16———————13.64
SVD-LLMComp. Rate=60%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1239.5———————15.29
SkipCatComp. Rate=80%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1232.82———————21.97
SVD-LLMComp. Rate=80%, Base Model=LLaMA2-7B, Fine-tuning=LoRA (Alpaca)2025.1232.33———————22.47
DenseSparsity=0%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—77.7476.0268.9874.5846.2544.279.05—
FLAPSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—44.7156.5861.7253.8331.233771.27—
LLM surgeonSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12——60.7261.0963.0936.69—73.56—
LLM surgeonSparsity=40%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12——48.0454.3852.3130.29—69.26—
ModeGPTSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12——63.2667.3263.2638.73—70.4—
ModeGPTSparsity=40%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12——53.0161.9649.4530.03—64.96—
O-FANGSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—63.0667.3367.3267.3439.9340.473.45—
O-FANGSparsity=40%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—61.1958.7264.4858.1633.1140.268.82—
OBCSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—64.6864.3466.0662.8836.4338.272.58—
OBCSparsity=40%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—6352.0460.6255.6831.1437.667.19—
SliceGPTSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—38.3249.0960.6949.5831.7432.664.91—
SliceGPTSparsity=40%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12——34.853.4336.4924.57—54.9—
SoBPSparsity=30%, Backbone=LLaMA2-7B, Evaluation Protocol=Zero-Shot2025.12—71.1967.2766.2259.8137.6338.473.5—