# Llama 4 Maverick: RAM and VRAM requirements

> Llama 4 Maverick is a 400B Llama 4 model (Mixture-of-Experts, 17B active per token). At Q4_K_M it needs about **231.7 GB** to run and fits **0 of 40** tracked devices. Minimum to run: high-memory hardware.

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 226.09 GB | ~231.7 GB |
| Q8_0 | 396.57 GB | ~402.2 GB |
| FP16 | 801 GB | ~806.6 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): No, not enough memory
- **Apple M4 Pro (48GB)** (48 GB): No, not enough memory
- **Apple M3 Ultra (256GB)** (256 GB): No, not enough memory

Full table of all 40 devices: https://localmodel.run/model/llama-4-maverick

## How to run
Quickest path: `ollama run llama4:128x17b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 400B (MoE, 17B active per token)
- Default context: 1000k tokens
- License: Llama 4 Community License (commercial use: conditional)
- Released: 2025-04
- HuggingFace: 43,543 downloads/mo, 505 likes

## FAQ
### How much VRAM or RAM does Llama 4 Maverick need?
About 231.7 GB at Q4_K_M (weights 226.09 GB + KV cache + overhead) at a 4k context. Budget ~402.2 GB for Q8_0.
### Can Llama 4 Maverick run on a laptop?
Llama 4 Maverick is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use Llama 4 Maverick commercially?
Conditionally: Llama 4 Community License; commercial use allowed below Meta's user threshold..

Sources: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct, https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF, https://ollama.com/library/llama4, https://aider.chat/docs/leaderboards/, https://gorilla.cs.berkeley.edu/leaderboard.html
More: https://localmodel.run/model/llama-4-maverick