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
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
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
- No model signature file is published with the weights.
- Built on meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8.
What the Hub's scanners report
43 weight files, 42 with a scan result. No scanner reports an issue with them.
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.
- 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
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.
- vllm · 131 advisories
- transformers · 24 advisories
- keras · 20 advisories
- onnx · 17 advisories
- bentoml · 16 advisories
- github.com/ollama/ollama · 16 advisories
- torch · 13 advisories
- lmdeploy · 10 advisories
- sglang · 10 advisories
- skops · 4 advisories
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.