Computational Model Studio · Model release

Llama 4 Maverick 17B-128E

Generate text from text and image prompts using Meta’s Maverick multimodal release.

Developer: Meta · Last verified:

What it is designed to do

Generate text from text and image prompts using Meta’s Maverick multimodal release.

Primary contribution
inference planning
Input
text, image
Output
text (generated text response)

Documented uses: Generate text from text and image prompts using Meta’s Maverick multimodal release.

Access and deployment

Technical profile and review notes
Construction
learned
Representation
neural
Normalized architecture tags
No normalized architecture tag assigned
Lifecycle
active

Inclusion rationale: Maverick is a distinct 128-expert Llama 4 release; visitors can compare its publisher artifact and gated access with Scout.

Limitations

  • The reviewed publisher source establishes the listed task and modalities, not independent accuracy or reliability measurements.
  • Repository availability does not establish a local hardware requirement or measured deployment profile.
  • Publisher weights require Meta license acceptance and access approval.

Sources and related Studio records

Sources

  1. Llama 4 Maverick model cardMeta · checked 2026-10-04
  2. Llama 4 Maverick repository filesMeta · checked 2026-10-04

Connections