Llama 4 Maverick 17B 128E Instruct FP8
Llama 4 Maverick 17B 128E Instruct FP8 is Meta's natively multimodal Mixture of Experts (MoE) model with 17B active parameters across 128 experts. Published benchmarks span image and text tasks, and the MoE activates a fraction of the parameters that comparable dense models use.
Tool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'meta/llama-4-maverick', prompt: 'Why is the sky blue?'})More models by Meta
| Model |
|---|
| 131K | 0.2s | 178tps | $0.17/M | $0.66/M | — | — |    | 04/05/2025 | |||||
| 128K | 0.2s | 141tps | $0.59/M | $0.72/M | — | — | | 12/06/2024 | |||||
| 128K | 0.3s | 54tps | $0.15/M | $0.15/M | — | — | | 09/18/2024 | |||||
| 128K | 0.2s | 88tps | $0.10/M | $0.10/M | — | — | | 09/18/2024 | |||||
| 131K | 0.1s | 41tps | $0.10/M | $0.10/M | Read:$0.1/M Write:— | — | — |  +2 | 07/23/2024 | ||||
| 131K | 0.4s | 31tps | $0.72/M | $0.72/M | — | — | | 07/23/2024 |
