DeepSeek Releases V4-Pro Model with FP8 Quantization

deepseek-ai · hf · 2026-08-13

DeepSeek has released its new model DeepSeek-V4-Pro-0813 on Hugging Face. Built on the Transformers architecture for text generation, the model features fp8 and 8-bit quantization. It is released under the MIT license and is compatible with various inference endpoints.

Related event: DeepSeek-V4-Pro Officially Released with Enhanced Agent Capabilities and Peak Pricing(48 posts)→

Original post →

More from Models

Models channel →