Open-weight local LLM

Llama 4 Scout (17B/16E MoE)

Catalogue summary: Meta's multimodal MoE model. 17B active params across 16 experts (~109B total). Built-in image understanding. 10M token context window. Apache 2.0. 728K downloads.

Repository editorial metadata; verify comparative claims in the linked upstream material.

16 GB catalogue minimum16 GB RAMQ4_K_MVision tasks
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
17B active (109B total, 16 experts)
Minimum RAM
16 GB
Model size
10 GB
Quantization
Q4_K_M

Can Llama 4 Scout (17B/16E MoE) run locally?

Llama 4 Scout (17B/16E MoE) has a catalogue minimum of 16 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use llama-4-scout as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

chatvisionpowergeneral

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch llama-4-scout in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: llama
  • Parameters: 17B active (109B total, 16 experts)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 16 GB
  • Catalogue model size: 10 GB
  • Tags: chat, vision, power, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • vision
  • power
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
6
quality
8
coding
8
reasoning
8

Technical notes

Developer
Meta AI
License
See upstream repository
Context window
131,072 tokens
Architecture
Mixture of Experts (MoE) with native vision

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Where to go next