Model · Meta · Text
Llama 4 Maverick
Meta's flagship Llama 4 model — natively multimodal, larger MoE architecture than Scout. The Llama 4 frontier-tier entry.
- Modality
- Text
- License
- Llama 4 Community License (Open weights)
- Parameter size
- 17B active / 128E
- Released
- April 5, 2025
- Last verified
- September 8, 2026
- Runs locally
- Yes
- Also handles
- vision
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 256 GB (512 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- Server only. Needs a server with several graphics cards, about 320 GB (640 GB recommended) of video memory in total — not a desktop PC.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Only a 256 GB or 512 GB Mac Studio (Ultra chip) can hold it; otherwise it needs a multi-GPU server.
Numbers are for: 4-bit build of the 400B model (about 230 GB). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Larger MoE expert count than Scout — more capacity per token
- Native multimodal across text and vision
- Strong instruction following at frontier scale
Weaknesses
- Heavier deployment footprint than Scout
- Community License restricts use at >700M MAU
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Gated — accept Community License |
| OpenRouter | hosted-api | API key required |
Version history
- Llama 4 Maverick Apr 2025 Current
- Llama 4 Scout Apr 2025
Official sources
- Model card model
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from 400B size at 4-bit.
- — Release date corrected to 2025-04-05, Meta's actual Llama 4 launch. The previous 2025-05-22 was the Hugging Face repo push timestamp. Still the newest Llama — there is no Llama 5; Meta's open-weight work moved to the Muse family (see Muse Glimmer 30B).
- — Initial entry. Sighted on Hugging Face (lastModified 2025-05-22).
Esc