NexaQuant Models - a NexaAI Collection

NexaAI 's Collections

Apple Neural Engine

Qualcomm NPU IoT

Qualcomm NPU Mobile

Qwen3VL

Multimodal - MLX

Multimodal - GGUF

NexaQuant Models

NexaQuant Models

updated Nov 25, 2025

NexaQuant compresses models with 100% accuracy recovery.

NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

8B • Updated Feb 19, 2025 • 82 • 90
NexaAI/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant

2B • Updated Feb 19, 2025 • 158 • 93