DeepSeek-V4-Pro-Base

Checkpointdeepseek-ai/DeepSeek-V4-Pro-BaseMetadata indexedModel card

Support summary

DeepSeek-V4-Pro-Base is a checkpoint published by DeepSeek, built on the DeepseekV4ForCausalLM architecture. vLLM lists its architecture, but not this exact checkpoint.

Configured context: 1,048,576 tokens

Hugging Face metadata

Publisher: DeepSeek
Architecture: DeepseekV4ForCausalLM
Weight tensor elements: 1.6T
Tensor types: BF16, I64, F32, F8_E4M3
Quantization: fp8
Configured context: 1,048,576 tokens
Weight access: Public
Repository created: 2026-04-22

Source 1 Source 2Reviewed 2026-09-05

Model notes and sources

deepseek-ai/DeepSeek-V4-Pro-Base · Hugging Face metadata
deepseek-ai/DeepSeek-V4-Pro-Base · publisher configuration
Reviewed 2026-09-05

Engine support

3 engines

Engine support for DeepSeek-V4-Pro-Base
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	Architecture listed; exact checkpoint unknown	No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1