AI PLATFORMS & MODELS
OPEN WEIGHTSOPEN SOURCE SELF-HOSTABLE

Llama 4 Maverick

by Meta

Meta’s open multimodal MoE for builders.

90HYLAND SCORE
11.2k views this week
Try Llama 4 Maverick
SHARE Post on X LinkedIn

Overview

Llama 4 Maverick is Meta’s open-weight multimodal mixture-of-experts model with a 1M token context. Designed for developers, it runs on major clouds and inference providers and can be fine-tuned and self-hosted under the Llama community license.

Key features

  • 400B MoE with 17B active parameters
  • Native multimodal (text + image)
  • 1M token context window
  • Broad provider support (Groq, Together, Fireworks)
  • Llama community license

Tags

Self-HostMultimodalMoEFine-tuning

Related in AI Platforms & Models

FEATURED VERIFIED

DeepSeek R1

DeepSeek
93HYLAND

Open-weight reasoning that rivals the frontier.

Open WeightsOpen Source Self-host
15.3k/wk
View
VERIFIED
92HYLAND

Self-hosted AI, privacy-critical apps

Open WeightsOpen Source Self-host
View
FEATURED VERIFIED

Kimi K2

Moonshot AI
91HYLAND

Open trillion-parameter agentic intelligence.

Open WeightsOpen Source Self-host
12.8k/wk
View