LLM
Unreleased
Open weights
Llama 4 Behemoth
Teacher model / research
Release2025-04
Context1M
Max output—
Parameters2T
Local / VRAMLocal
LicenseOpen weights
Overview
Llama 4 Behemoth is a model in the LLM category from Meta AI. It was released in 2025-04. The vendor is based in US. Best for: Teacher model / research.
Strengths
- 2T parameters
- Used to distill Scout/Maverick
Limits
- Not publicly available
- Not usable in production
Specifications
| Vendor | Meta AI |
|---|---|
| Category | LLM |
| Release | 2025-04 |
| Status | Unreleased |
| License | Open weights |
| License name | Llama 4 Community License |
| Commercial use | Not specified |
| Parameters | 2T |
| Active parameters | 288B |
| Architecture | MoE transformer |
| Context window | 1M |
| Input modalities | Text, Image |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| API access | Yes |
| Pricing | Not released |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Frontier lab |
Pricing & hardware
Not released
This model can be self-hosted or run locally. API access is available.