List your company

Text Generation on IFEval

74.49AccuracyLlama 3.1 8B Instruct
68.343669.939371.53573.1307May 28, 2026

Evaluation results

MethodLinks
Llama 3.1 8B Instruct# Bits=BF16, Decoding Strategy=greedy2026.0574.49
Llama 3.1 8B Instruct# Bits=BF16, Decoding strategy=greedy2026.0574.49
FlexRound+LFQ+RILQ# Bits=W4, PTQ Method=FlexRound, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0572.46
FlexRound+LFQ# Bits=W4, PTQ Method=FlexRound, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0572.09
FlexRound+LFQ# Bits=W4, Decoding strategy=greedy2026.0572.09
FlexRound+RILQ# Bits=W4, PTQ Method=FlexRound, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0571.9
FlexRound+RILQ# Bits=W4, Decoding strategy=greedy2026.0571.9
OmniQuant+RILQ# Bits=W4, PTQ Method=OmniQuant, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0571.35
OmniQuant+LFQ# Bits=W4, PTQ Method=OmniQuant, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0571.35
OmniQuant+LFQ+RILQ# Bits=W4, PTQ Method=OmniQuant, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0571.35
OmniQuant+RILQ# Bits=W4, Decoding strategy=greedy2026.0571.35
OmniQuant+LFQ# Bits=W4, Decoding strategy=greedy2026.0571.35
OmniQuant# Bits=W4, PTQ Method=OmniQuant, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0570.61
OmniQuant# Bits=W4, Decoding strategy=greedy2026.0570.61
FlexRound# Bits=W4, PTQ Method=FlexRound, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0570.24
FlexRound# Bits=W4, Decoding strategy=greedy2026.0570.24
Block-AP+LFQ# Bits=W4, PTQ Method=Block-AP, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0568.76
Block-AP+LFQ# Bits=W4, Decoding strategy=greedy2026.0568.76
Block-AP# Bits=W4, PTQ Method=Block-AP, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0568.58
Block-AP+RILQ# Bits=W4, PTQ Method=Block-AP, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0568.58
Block-AP+LFQ+RILQ# Bits=W4, PTQ Method=Block-AP, Decoding Strategy=greedy, Quantization Granularity=4-bit per-channel weight-only2026.0568.58
Block-AP# Bits=W4, Decoding strategy=greedy2026.0568.58
Block-AP+RILQ# Bits=W4, Decoding strategy=greedy2026.0568.58