DeepHermes 3 Mistral 24B Preview

This is an FP8 dynamic quantization of NousResearch/DeepHermes-3-Mistral-24B-Preview

Downloads last month
56
Safetensors
Model size
23.6B 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 qingy2024/DeepHermes-3-Mistral-24B-Preview-FP8-dynamic

Collection including qingy2024/DeepHermes-3-Mistral-24B-Preview-FP8-dynamic