"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization Paper • 2411.02355 • Published 23 days ago • 45
Llama-3.1 Quantization Collection Neural Magic quantized Llama-3.1 models • 22 items • Updated 5 days ago • 39
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Non-Uniform-compressed-tensors Text Generation • Updated Jul 17 • 5