Model Spend Arena2ND ED.
862B · MoE · 1,048,576 ctx · 2026-08-14

DeepSeek V4 Pro

Runs on Data centre · Hugging Face ↗

vLLMSGLang

Coding index 68.8 (Artificial Analysis)

A very large MoE and one of the highest-scoring open coding models. The weights are open, but running it is a multi-node affair.

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈4 GB at 32K, fp16).

QuantizationSize
Q4849.7 GB
Q8873.4 GB

Config tips

Hundreds of GB even at Q4 — tensor / pipeline parallel across many GPUs with vLLM or SGLang. For anything short of a cluster, rent it per token (leaderboard).