This is a checkpoint for quantization using llm-compressor, supporting vllm, sglang inference.

Downloads last month
8
Safetensors
Model size
70.6B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jiangchengchengNLP/L3.3-MS-Nevoria-70b-FP8-Dynamic

Quantized
(28)
this model