Llama 4 Maverick

Hot

Meta's flagship open-weight MoE with 128 experts and 1M context, distilled from Llama 4 Behemoth

Model Specifications

ArchitectureVISION

Parameters400B

Familyllama

VRAM (Q4)200.0GB

Mixture of ExpertsActive inference parameters: 17B.

Available in BF16 and FP8 quantized weights

#meta#moe#multimodal#flagship#trendingSource

Send this model's specs directly to your community.

Refined Llama 3 with superior following

Mobile-optimized small model

Ultra-light edge deployment

A complete breakdown of quantization levels and VRAM overhead for running local models.

Comparing NVIDIA and AMD options for the best speed-to-dollar ratio.

Understanding local AI formats and which one to pick for your specific hardware.