UTC

Llama 3.1 8B Instruct

Meta · open weights · served by 22 providers · tool calling

meta/llama-3.1-8b-instruct

Weights
Open
Released
2024-07-23
Knowledge cutoff
2023-12
Context window
16K
Deprecation dates

When each platform deprecates Llama 3.1 8B Instruct, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Amazon Bedrockdeprecates 2027-03-30meta.llama3-1-8b-instruct-v1:0successor: meta.llama2-13b-chat-v1
Every upcoming deprecation →
Hugging Face repository

meta-llama/Llama-3.1-8B-Instruct at commit 0e9e39f249, last changed 2024-09-25

Licence
llama3.1
Access
Gated (approval)
Library
transformers
Formats
.pth .safetensors
  • 1 weight file uses a pickle-based format, which can run code when loaded. Load the safetensors files instead.
  • No model signature file is published with the weights.
  • Built on meta-llama/Meta-Llama-3.1-8B.

What the Hub's scanners report

5 weight files, 5 with a scan result. No scanner reports an issue with them.

The model at this commit, its 5 weight files and its base models. The Hub shows file hashes of a gated model only after you accept its licence.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • Abacusmeta-llama/Meta-Llama-3.1-8B-Instructdeprecated
  • Amazon Bedrockmeta.llama3-1-8b-instruct-v1:0deprecated
  • Amazon Bedrockus.meta.llama3-1-8b-instruct-v1:0deprecated
  • Atomic ChatMeta-Llama-3_1-8B-Instruct-GGUF
  • Cloudflare Workers AI@cf/meta/llama-3.1-8b-instruct-fp8deprecated
  • Groqllama-3.1-8b-instantdeprecated
  • Heliconellama-3.1-8b-instant
  • Heliconellama-3.1-8b-instruct
  • Heliconellama-3.1-8b-instruct-turbo
  • Hugging Facemeta-llama/Llama-3.1-8B-Instruct
  • Inferencemeta/llama-3.1-8b-instructdeprecated
  • Kilo Gatewaymeta-llama/llama-3.1-8b-instruct
  • Kitanimeta-llama/llama-3.1-8b-instruct
  • Merge Gatewaymeta/llama-3.1-8b-instruct
  • NanoGPTmeta-llama/llama-3.1-8b-instruct
  • Neonmeta-llama-3-1-8b-instruct
  • Novita AImeta-llama/llama-3.1-8b-instruct
  • OpenRoutermeta-llama/llama-3.1-8b-instruct
  • Poecerebras/llama-3.1-8b-cs
  • Vercel AI Gatewaymeta/llama-3.1-8b
  • CoreWeavemeta-llama/Llama-3.1-8B-Instruct
  • ZeroGPUllama-3.1-8b-instruct-fast
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.