Llama Guard 4 12B
meta/llama-guard-4-12b- Meta
- Family · Llama Guard 4
- Open weights
- Image · Text → Text
- Vision
Not on OSMEXO yet
Spec & list price
Context160K
Max output16K
Input / 1M$0.18
Output / 1M$0.181× input
Usage
Tokens / day591.9M▲ 16% 7d
Usage rank#219
Requests / day364.7K
Per request · 30 days
Avg input9580.1× median
Avg output40.0× median
Consumption
Peak 712.9M 20 OctLow 154.0M 13 OctRank today #219
News & trends
News · latest from Meta
- Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI NetworksMeta Engineering · 26 Oct
- Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72NVIDIA · 15 Oct
- Meta Muse Spark Open is live on Together AITogether AI · 15 Oct
- Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta15 Oct
Speed
Output speed#332/33410 tok/s6.3× slower than median
First token#240.38 s2.9× quicker than median
Technical details
- Tokenizer
- Other
- Knowledge cutoff
- 2024-08-31
- License
- other
- Parameters
- 12B
- Moderation
- none
- Downloads · likes
- 86.8K · 136
Request parameters 11
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- presence_penalty
+1 more
- repetition_penalty
When to use
Best for
- Content moderation for prompts and replies
- Safety screening of image and text input
- Guardrail checks in front of other models
Think twice for
- General chat
- Coding agents
- Creative writing
- Tool calling workflows
Want Llama Guard 4 12B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.