# Llama 3.3 70B Instruct FP8

Llama 3.3 70B Instruct FP8 is a model from NVIDIA with open weights, first recorded on 11 Nov 2026; its release date is not established.

- Developer: NVIDIA
- Id: nvidia/Llama-3.3-70B-Instruct-FP8
- Sighting: 2026-11-11T21:23:55.161Z
  - [evidence link](https://huggingface.co/nvidia/Llama-3.3-70B-Instruct-FP8)
- Status: Released
- Weights version: 2025-05-06
  - [evidence link](https://huggingface.co/api/models/nvidia/Llama-3.3-70B-Instruct-FP8/paths-info/fde04ee76a27704c88f569542ef023b57d4d0362)
- Canonical: https://alexgetman.com/models/nvidia/llama-3-3-70b-instruct-fp8/

## Questions

### Are the weights of Llama 3.3 70B Instruct FP8 publicly available?

Yes. NVIDIA publishes the weights.

### When was Llama 3.3 70B Instruct FP8 released?

Its release date is not established. Signal Forge first recorded it on 11 Nov 2026.

## Evidence links

- [hf-author-artifacts:nvidia](https://huggingface.co/api/models/nvidia/Llama-3.3-70B-Instruct-FP8/paths-info/fde04ee76a27704c88f569542ef023b57d4d0362)
- [huggingface:nvidia](https://huggingface.co/nvidia/Llama-3.3-70B-Instruct-FP8)

## Signals