EOQ Compressed Models - a caiovicentino1 Collection

caiovicentino1 's Collections

PolarQuant Video & Diffusion Models

PolarQuant Gemma Models

Nemotron 30B — Consumer GPU Inference

PolarQuant Unified (Weights Q5 + KV Cache Q3)

PolarQuant MLX (Apple Silicon)

PolarQuant Models

Large Models (27B-35B)

Qwen3.5-4B EOQ Quantized

Qwen2.5 EOQ Quantized

Qwen3.5-9B PolarQuant

EOQ Compressed Models

Qwen3.5-27B PolarQuant

EOQ Compressed Models

updated 9 days ago

EOQ (Entropy-Optimal Quantization) compressed models. Mixed-bit allocation + rANS entropy coding. Smaller download, dequant at load time.