inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_5.75-bits
6B
•
Updated
•
15
Mixed Precision Models
Collection of Mixed Precision LLaMA and Qwen Models
-
-
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_6.0-bits
6B • Updated • 18 -
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_5.0-bits
5B • Updated • 34 -
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_5.25-bits
6B • Updated • 14 -
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_5.5-bits
6B • Updated • 15 -
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_6.25-bits
6B • Updated • 12 -
inference-optimization/Meta-Llama-3.1-8B-Instruct-NVFP4-FP8-Dynamic_6.5-bits
7B • Updated • 17