runlocal.devCheck My GPU →

DeepSeek V4 Pro

MoEDeepSeek

DeepSeek's frontier 1.6T MoE, trained with FP4 QAT at scale. Novel Hybrid Attention (CSA+HCA) and Manifold-Constrained Hyper-Connections replace residuals. $1.74/$3.48 per M tokens via API; not local-runnable.

Provider

DeepSeek

Parameters

862B active / 1.6T total (MoE)

Context

128K

Released

2026-04-24

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
BF16 (reference)2900 GB3100 GB0 GPUs

Benchmark Scores

mmlu91%
humaneval93.5%

Scores are approximate and may vary by quantization level.

HuggingFace

deepseek-ai/DeepSeek-V4-Pro

View on HF →