RUN THIS LLM

Search local LLM hardware requirements

← Back to all models

DeepSeek V4 Flash

DeepSeek · 284B MoE · General

284B MoE with 13B active params and 256 experts. Efficiency-focused sibling of V4 Pro — hybrid attention cuts KV cache to ~10% of V3 while keeping a 1M-token context.

VRAM Requirements

QuantizationVRAM
Q4_K_M (smallest)170.4 GB
Q8_0 (balanced)312.4 GB
FP16 (full quality)568 GB

Specifications

Benchmarks

Loading interactive analysis...

RTL
Add Run This LLM to your home screen
Get the Chrome Extension
Look up hardware requirements for any model right from your browser sidebar — no tab switching needed.
Add to Chrome — It's Free