v2.2 · 2026-06-12

VISION / MULTIMODAL MODEL — RUNTIME REQUIREMENTS

·LM Studio Scout GGUF page notes text-only support for now, despite the official model being multimodal.

·Commercial-use status from the supplied research: 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.

·Beginner summary from supplied research: 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.

Llama 4 Scout

llama-4-scout

MULTIMODAL

Llama 4 Scout is a 109B multimodal model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

Meta

FAMILY

Llama 4

MODEL TYPE

multimodal

PARAMETERS

109B (17B active)

MODALITIES

multilingual text input, image input, text output, code output

ARCHITECTURE

Mixture-of-experts autoregressive LLM with early-fusion multimodality; 16 experts

CONTEXT WINDOW

10,000,000 tokens

TRAINING TOKENS

—

RELEASE DATE

2025-04-05

LICENSE & LINKS

Llama 4 Community Licenselicense text

MODEL CARD

huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct

HUGGING FACE

meta-llama/Llama-4-Scout-17B-16E-Instruct

GGUF REPOSITORIES

lmstudio-community/Llama-4-Scout-17B-16E-Instruct-GGUF community conversion

Community GGUF repository referenced by the June 2026 model research.

SETUP HINTS

OLLAMA

ollama run llama4:scout

LM STUDIO

Available according to the supplied June 2026 research; select a cited GGUF/MLX build and verify current app metadata before relying on hands-on setup guidance.

LLAMA.CPP

Use the cited GGUF repository (lmstudio-community/Llama-4-Scout-17B-16E-Instruct-GGUF) with current llama.cpp-compatible tooling.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

67.5 GB

Q8_0

113 GB

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

RAM / VRAM ESTIMATES

MIN RAM

80 GB

COMFORTABLE RAM

128 GB

MIN VRAM

80 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

8 GB RAM

16 GB RAM

32 GB RAM

8 GB VRAM

12 GB VRAM

24 GB VRAM

Apple Silicon (unified memory)

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

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

AVOID IF

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

CAVEATS

·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.

SOURCE URLS