Skip to content
Back to the index

Llama 3.3 70B Instruct

huggingface.coInfrastructure🇺🇸

PulseGate's liveness check found it on 3 Oct 2026; it is registered on Hugging Face and has been in the index since 26 Jul 2026. How this is checked

nvidia/Llama-3.3-70B-Instruct-FP8 provides an FP8-quantized version of Meta's Llama 3.3 70B Instruct model. It includes optimized inference support and a chat template with built-in tool calling capabilities. The model is designed for efficient local or self-hosted deployment using NVIDIA hardware and inference stacks.

Inferred · not functionally tested

Open SourceApache-2.0WebCLISelf-hosted
Llama 3.3 70B Instruct preview
Visit huggingface.co
3.3kstars
514forks
21alternatives
4features
2024since

Overview

4 features

Purpose: Running a high-performance 70B parameter language model efficiently on GPU hardware with reduced memory requirements.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: code_generation, agents

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: WEB · deployment: browser, cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: huggingface.co. These links do not verify the individual claims.

In the Quantised & converted weights space, Llama 3.3 70B Instruct takes a focused approach. Inferred · not functionally tested: It focuses on running a high-performance 70B parameter language model efficiently on GPU hardware with reduced memory requirements. Inferred · not functionally tested: Llama 3.3 70B Instruct is an open-source project aimed at developers. Basis unknown · not verified: Llama 3.3 70B Instruct is open source under the Apache-2.0 license. Basis unknown · not verified: Llama 3.3 70B Instruct is available on the web and the command line, and it can be self-hosted.

It is developed by NVIDIA (United States), and it first shipped in 2024. Development happens publicly on GitHub with 3.3k stars and 354 commits in the last 90 days. The category is crowded — PulseGate's index counts 21 comparable projects. Inferred · not functionally tested: Key capabilities include Instruction Tuning, Quantized Inference, and Chat Template.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Instruction Tuning
  • Quantized Inference
  • Chat Template
  • Tool Use

Topics: Inferred · not functionally tested

Tags
llama3instruct-modelquantized-llm70b-model
AI capabilities
Text
Weights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Hosting
AWS
AI providers
local_ossmeta_llama
Runs on
BrowserCLISelf-hosted
Detected from
AWS
x-amz-cf-id header · x-amz-cf-pop header · via header
local_oss
bvllm in the HTML
meta_llama
llama- in the HTML

Trust & compliance

License
Apache-2.0
Public signals
HTTPSPrivacy PolicyTerms of ServiceOpen SourceFree tierActive maintenance
Legal
Privacy Policy Terms of Service

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed26 Jul · 09:41 UTC
    nvidia/Llama-3.3-70B-Instruct-FP8 seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open

Frequently asked questions about Llama 3.3 70B Instruct

What does Llama 3.3 70B Instruct do?
Inferred · not functionally tested: Llama 3.3 70B Instruct focuses on running a high-performance 70B parameter language model efficiently on GPU hardware with reduced memory requirements. It is catalogued under Quantised & converted weights on PulseGate.
Who is Llama 3.3 70B Instruct for?
Inferred · not functionally tested: Llama 3.3 70B Instruct is an open-source project built for developers.
Is Llama 3.3 70B Instruct free?
Basis unknown · not verified: Yes — Llama 3.3 70B Instruct is open source under the Apache-2.0 license and free to use.
What platforms does Llama 3.3 70B Instruct run on?
Basis unknown · not verified: Llama 3.3 70B Instruct runs on the web and the command line. It can also be self-hosted.
Is Llama 3.3 70B Instruct still active?
PulseGate's liveness check found it on 3 Oct 2026. Its GitHub repository shows 354 commits in the last 90 days.
What are alternatives to Llama 3.3 70B Instruct?
Similar projects tracked by PulseGate include Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, and Llama 3.1 8B Instruct.Llama 3.3 70B InstructLlama 3.1 8B InstructLlama 3.1 8B Instruct
Who develops Llama 3.3 70B Instruct?
Llama 3.3 70B Instruct is developed by NVIDIA, based in the United States.
When did Llama 3.3 70B Instruct launch?
Llama 3.3 70B Instruct first shipped in 2024.

Similar projects

Closest matches by what these projects do