# Llama 4 Maverick 17B 128E Instruct FP8

Llama 4 Maverick 17B 128E Instruct FP8 is a model from Meta with open weights, first recorded on 7 Oct 2026; its release date is not established. The context window is 1,048,576 tokens.

- Developer: Meta
- Id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
- Sighting: 2026-10-07T19:40:57.518Z
  - [evidence link](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8)
- Status: API availability
- Canonical: https://alexgetman.com/models/meta/llama-4-maverick-17b-128e-instruct-fp8-818/

## Questions

### What is the context window of Llama 4 Maverick 17B 128E Instruct FP8?

The context window is 1,048,576 tokens.

### Are the weights of Llama 4 Maverick 17B 128E Instruct FP8 publicly available?

Yes. Meta publishes the weights.

### When was Llama 4 Maverick 17B 128E Instruct FP8 released?

Its release date is not established. Signal Forge first recorded it on 7 Oct 2026.

## Evidence links

- [Arena · leaderboards](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct)
- [huggingface-router](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8)
- [Azure Foundry · lifecycle](https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement?view=azureml-api-2)
- [models.dev · catalogue](https://models.dev/#Llama-4-Maverick-17B-128E-Instruct-FP8)
- [models.dev · catalogue](https://models.dev/#llama-4-maverick-17b-128e-instruct)
- [models.dev · catalogue](https://models.dev/#llama-4-maverick-17b-128e-instruct-fp8)
- [models.dev · catalogue](https://models.dev/#llama-4-maverick-17b-128e-instruct-maas)
- [OpenRouter · usage](https://openrouter.ai/rankings)

## Signals

- [Llama 4 Maverick 17B 128E Instruct FP8 spotted on Arena](https://alexgetman.com/signals/2026/09/13/llama-4-maverick-17b-128e-instruct/)