ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Paper
•
2511.10645
•
Published
•
6
ParoQuant
ParoQuant 4-bit quantized models
-
-
z-lab/Meta-Llama-3-8B-PARO
1B • Updated • 33 -
z-lab/Meta-Llama-3-70B-PARO
20B • Updated • 3 -
z-lab/Llama-3.1-8B-Instruct-PARO
3B • Updated -
z-lab/Llama-2-7b-hf-PARO
2B • Updated -
z-lab/DeepSeek-R1-Distill-Llama-8B-PARO
1B • Updated • 4 -
z-lab/Qwen3-0.6B-PARO
0.3B • Updated -
z-lab/Qwen3-1.7B-PARO
0.7B • Updated -
z-lab/Qwen3-4B-PARO
1B • Updated • 10 -
z-lab/Qwen3-8B-PARO
1B • Updated • 409 -
z-lab/Qwen3-14B-PARO
2B • Updated -
z-lab/Qwen3-0.6B-Base-PARO
0.3B • Updated -
z-lab/Qwen3-1.7B-Base-PARO
0.7B • Updated -
z-lab/Qwen3-4B-Base-PARO
1B • Updated -
z-lab/Qwen3-8B-Base-PARO
1B • Updated • 8 -
z-lab/Qwen3-14B-Base-PARO
2B • Updated -
z-lab/Qwen3-4B-Thinking-2507-PARO
1B • Updated -
z-lab/paroquant-checkpoints
Updated