Llama 4 Scout

Who should use this model?

• Long documents, image questions, and advanced local experiments on H100-class or high-memory workstation hardware setups.

Choose something else when

• Avoid for ordinary laptops, low-RAM PCs, EU users, or anyone needing easy setup today locally.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only

Use a smaller model for this memory limit.

8GB system memory

Use a smaller model for this memory limit.

16GB system memory

Use a smaller model for this memory limit.

32GB system memory

Use a smaller model for this memory limit.

8GB GPU memory

Use a smaller model for this memory limit.

12GB GPU memory

Use a smaller model for this memory limit.

24GB GPU memory

Use a smaller model for this memory limit.

Apple unified memory

Use a smaller model for this memory limit.

Model facts that change the decision

Parameters

109B total / 17B active

Input

Multilingual text input · Image input · Text output · Code output

Published context limit

10,000,000 tokens

Model format

safetensors · GGUF · Ollama · MLX

Suggested compression

Q4_K_M for first local attempts unless a cited runtime recommends a different default.

Typical Q4 file

67.5GB before runtime and context overhead

Languages

Unknown

Using image input

This model needs an app or library that supports its image-processing components. Follow the exact model’s instructions for preparing image inputs. Some GGUF downloads also need a matching projector file; loading the text model alone does not establish image support.

Conditions that change the answer

• The 10M-token context is an official maximum, but Meta says context lengths were evaluated across 512 GPUs.
• MoE lowers active compute but not stored-weight memory; the full 109B parameters still matter for RAM/VRAM.
• Official Scout release is BF16; on-the-fly INT4 can fit an H100, but beginner local users will usually need community GGUF/MLX quants.
• LM Studio Scout GGUF page notes text-only support for now, despite the official model being multimodal.
• Llama 4 uses a custom Meta license, not Apache 2.0.
• Commercial use: Permitted for commercial and research use subject to Meta's custom Llama 4 Community License, Acceptable Use Policy, attribution requirements, 700M MAU threshold, and EU multimodal restriction.
• Llama 4 Scout is a huge, open-weight multimodal MoE model for long documents and image understanding. It is technically local only on serious hardware, with tiny quants trading quality for fit, especially at full context.