SinclairSchneider/Apertus-v1.5-8B-W4A16-KV8-de
Text Generation • 9B • Updated • 588
German-Calibrated Quantized Models
W4A16 and FP8 quantizations of open models, calibrated on German text with static fp8 KV-cache scales baked in.
W4A16 and FP8 quantizations of open models, calibrated on German text with static fp8 KV-cache scales baked in.