Llama 3.2 3B Instruct
Meta · open weights · served by 8 providers · tool calling
meta/llama-3.2-3b-instruct
- Weights
- Open
- Released
- 2024-09-25
- Knowledge cutoff
- 2023-12
- Context window
- 80K
When each platform deprecates Llama 3.2 3B Instruct, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.
- Together AIdeprecated 2026-07-29together_ai/meta-llama/Llama-3.2-3B-Instructsuccessor: together_ai/meta-models/Muse-Glimmer-30B
meta-llama/Llama-3.2-3B-Instruct at commit 0cb88a4f76, last changed 2024-10-24
- Licence
- llama3.2
- 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.
What the Hub's scanners report
3 weight files, 3 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.
- Autarchollama-32-3b-uncensored
- Eden AIcloudflare/@cf/meta/llama-3.2-3b-instruct
- Eden AIdeepinfra/meta-llama/Llama-3.2-3B-Instruct
- Hugging Facemeta-llama/Llama-3.2-3B-Instruct
- Kilo Gatewaymeta-llama/llama-3.2-3b-instruct
- NanoGPTmeta-llama/llama-3.2-3b-instruct
- OpenRoutermeta-llama/llama-3.2-3b-instruct
- Venice AIllama-3.2-3b
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.