Skip to content
Back to the index

Hermes 3 Llama 3.1 70B

huggingface.coInfrastructure

PulseGate's liveness check found it on 28 Sep 2026; it is registered on GitHub, the App Store and Google Play and has been in the index since 17 Jun 2026. How this is checked

Hermes-3-Llama-3.1-70B-FP8 is an FP8-quantized 70-billion-parameter language model published by NousResearch on Hugging Face. Developers and researchers can download and run the model locally or deploy it through compatible inference infrastructure.

Inferred · not functionally tested

Open SourceApache-2.0WebCLIAndroidAPI
Hermes 3 Llama 3.1 70B preview
Visit huggingface.co
83.2kstars
18.2kforks
6features
2023since

Overview

6 features

Purpose: Running and integrating a capable language model without relying on a proprietary hosted model.

Inferred · not functionally tested

Audience: AI developers and researchers

Inferred · not functionally tested

Functions: code_generation

Inferred · not functionally tested

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

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

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: huggingface.co · github.com · play.google.com. These links do not verify the individual claims.

Hermes 3 Llama 3.1 70B sits in PulseGate's Foundation models & chat category. Inferred · not functionally tested: It focuses on running and integrating a capable language model without relying on a proprietary hosted model. Inferred · not functionally tested: It is built as an open-source project for AI developers and researchers. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: Hermes 3 Llama 3.1 70B is available on the web, the command line, Android, and API.

NousResearch builds and maintains Hermes 3 Llama 3.1 70B, and it first shipped in 2023. The project is developed in the open on GitHub with 83.2k stars and 2.7k commits in the last 90 days. Inferred · not functionally tested: Key capabilities include text generation, chat template, and tool use. Inferred · not functionally tested: Catalogued interfaces include a public API.

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

Tasks: Inferred · not functionally tested

  • Text generation
  • Chat template
  • Tool use
  • Function calling
  • Open weights
  • FP8 quantization

Topics: Inferred · not functionally tested

Tags
llama-3.1fp8-quantizationopen-weightslanguage-model
AI capabilities
Text
Inference: LocalWeights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Hosting
AWS
AI providers
local_oss
Written with
Claude CodeCodexCursor
Connectors
API
Runs on
BrowserCLIAndroidAPI-only
Written with — evidence
Claude Code
commit 8cbd5d03006c · since Oct 2026
Codex
commit 201e537d98aa · since Oct 2026
Cursor
commit 81c993658e0b · since Oct 2026
Detected from
AWS
x-amz-cf-id header · x-amz-cf-pop header · via header
local_oss
bvllm in the HTML · huggingface in the HTML

Trust & compliance

License
Apache-2.0
Public signals
HTTPSPrivacy PolicyTerms of ServiceOpen SourceFree tierGitHub · ★ 83.2kActive maintenanceStore listing found
Legal
Privacy Policy Terms of Service

Indexing history

5

What PulseGate has recorded for this listing

  1. Indexed9 Oct · 12:44 UTC
    NousResearch/Hermes-3-Llama-3.1-70B-FP8 seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open
  2. Indexed28 Sep · 21:55 UTC
    GaleneAI/llama-3.1-nemoguard-8b-content-safety-merged-NVFP4 seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open
  3. Indexed24 Sep · 22:19 UTC
    sanskar003/Qwen3.5-4B-AWQ seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open
  4. Indexed24 Sep · 18:47 UTC
    Watermarking in vLLM seen via Hacker News firehose (Algolia)
    Source: Hacker News firehose (Algolia) · Open
  5. Indexed19 Sep · 19:31 UTC
    CohereLabs/cohere-transcribe-03-2026 seen via Hugging Face Enumerator
    Source: Hugging Face Enumerator · Open

Frequently asked questions about Hermes 3 Llama 3.1 70B

What is Hermes 3 Llama 3.1 70B?
Inferred · not functionally tested: Hermes 3 Llama 3.1 70B focuses on running and integrating a capable language model without relying on a proprietary hosted model. It is catalogued under Foundation models & chat on PulseGate.
Who should use Hermes 3 Llama 3.1 70B?
Inferred · not functionally tested: Hermes 3 Llama 3.1 70B is an open-source project built for AI developers and researchers.
How much does Hermes 3 Llama 3.1 70B cost?
Basis unknown · not verified: Hermes 3 Llama 3.1 70B is open source (Apache-2.0); commercial plans start at $4.99.
What platforms does Hermes 3 Llama 3.1 70B run on?
Basis unknown · not verified: Hermes 3 Llama 3.1 70B runs on the web, the command line, Android, and API.
Is Hermes 3 Llama 3.1 70B still maintained?
PulseGate's liveness check found it on 28 Sep 2026. Its GitHub repository shows 2.7k commits in the last 90 days.
Who develops Hermes 3 Llama 3.1 70B?
Hermes 3 Llama 3.1 70B is developed by NousResearch.
How long has Hermes 3 Llama 3.1 70B been around?
Hermes 3 Llama 3.1 70B first shipped in 2023.
Is Hermes 3 Llama 3.1 70B open source?
Basis unknown · not verified: Yes — Hermes 3 Llama 3.1 70B is open source under the Apache-2.0 license, developed on GitHub.

Similar projects

Closest matches by what these projects do

Submit to the index
Apps, agents and models — free, no signup.