Semifly
Open-weight · Meta

Llama 4 Scout

Meta's ultra-long-context model — up to 10 million tokens — ideal for entire document collections, research libraries, legal files, and large codebases.

Developer
Meta
Parameters
MoE
Context
10M
License
Llama 4
Run on Semifly →Download on Hugging Face

About Llama 4 Scout

Meta's ultra-long-context model — up to 10 million tokens — ideal for entire document collections, research libraries, legal files, and large codebases.

Parameters, context, and license as reported June 2026. Confirm the current license on the official Hugging Face page before deployment.

← Back to all models

Run any of these on Semifly

Tokens & API

Access hosted models through a simple, metered token API.

Get API access →

GPU servers

Buy or lease Supermicro GPU systems to self-host open-weight models.

Browse GPU servers →

AI Foundry

Managed compute for training, fine-tuning, and inference.

Explore AI Foundry →