HighDeprecation
Meta deprecating Llama-4-Maverick-17B-128E-Instruct-FP8
Action Required
Applications relying on the Llama-4-Maverick-17B-128E-Instruct-FP8 model will no longer function after April 15, 2026, requiring immediate migration planning.
AI Impact Summary
Meta is deprecating the Llama-4-Maverick-17B-128E-Instruct-FP8 model, effective April 15, 2026. This model is no longer available on serverless, impacting any applications currently utilizing it. Users should migrate to a supported model like Qwen/Qwen3-Coder-Next-FP8 or another compatible alternative to avoid service disruptions.
Meta deprecating Llama-4-Maverick-17B-128E-Instruct-FP8
Affected Systems
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
- Date
- Date not specified
- Change type
- deprecation
- Severity
- high