DeepSeek-V4-Flash-Vision-Exp-GGUF

Overview

The 4-bit cut of DeepSeek's experimental vision variant of V4-Flash - 284B MoE with 13B activated at higher fidelity, with multimodal agent scores well clear of the text-only release. Image input currently needs a preview llama.cpp build; needs 256 GB.

Recommended hardware

≈ 256 GB VRAM to run this 284B model at the UD-IQ4_XS quantization.

Needs 256 GB+ of VRAM (e.g. 2x 192 GB Blackwell, or 4x 80 GB H100)

Links

• View on HuggingFace
• Run on Infersec