UTC

Llama 4 Maverick 17B Instruct

Meta · open weights · served by 18 providers · tool calling, image input

meta/llama-4-maverick-17b-instruct

Weights
Open
Released
2025-04-05
Knowledge cutoff
2024-08
Context window
1.048576M
Deprecation dates

When each platform deprecates Llama 4 Maverick 17B 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.llama4-maverick-17b-instruct-v1:0
  • Azure AI Foundrydeprecated 2026-11-19azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8successor: azure_ai/Llama-4-Scout-17B-16E-Instruct
Every upcoming deprecation →
Hugging Face repository

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 at commit 94125d2bd8, last changed 2025-05-22

Licence
llama4
Access
Gated (approval)
Library
transformers
Formats
.safetensors

What the Hub's scanners report

43 weight files, 42 with a scan result. No scanner reports an issue with them.

The model at this commit, its 43 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/Llama-4-Maverick-17B-128E-Instruct-FP8deprecated
  • Amazon Bedrockmeta.llama4-maverick-17b-instruct-v1:0deprecated
  • Amazon Bedrockus.meta.llama4-maverick-17b-instruct-v1:0deprecated
  • Deep Inframeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8deprecated
  • DigitalOceanllama-4-maverick
  • Heliconellama-4-maverick
  • IO.NETmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  • Kilo Gatewaymeta-llama/llama-4-maverick
  • DevPass (LLM Gateway)llama-4-maverick-17b-instruct
  • LLM Gatewayaws-bedrock/llama-4-maverick-17b-instructdeprecated
  • LLM Gatewaynovita/llama-4-maverick-17b-instruct
  • NanoGPTmeta-llama/llama-4-maverick
  • Neonllama-4-maverick
  • Novita AImeta-llama/llama-4-maverick-17b-128e-instruct-fp8
  • OCI Generative AImeta.llama-4-maverick-17b-128e-instruct-fp8
  • OpenRoutermeta-llama/llama-4-maverick
  • Vercel AI Gatewaymeta/llama-4-maverick
  • watsonx.aimeta-llama/llama-4-maverick-17b-128e-instruct-fp8
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.