RedHatAI/Kimi-K2-Instruct-quantized.w4a16

Preliminary version of the model

Evaluations

• GSM8k, 5-shot via lm-evaluation-harness

moonshotai/Kimi-K2-Instruct                            = 94.92
RedHatAI/Kimi-K2-Instruct-quantized.w4a16 (this model) = 94.84

More evals coming very soon...