LLM
GA
Open weights
Llama 3.3 70B
Classic 70B self-host with a mature ecosystem
Release2024-12
Context131K
Max output—
Parameters70B
Local / VRAM40–48 GB
LicenseOpen weights
Overview
Llama 3.3 70B is a model in the LLM category from Meta AI. It was released in 2024-12. The vendor is based in US. Best for: Classic 70B self-host with a mature ecosystem.
Strengths
- Broad fine-tune/tooling support
- Q4 on a single 48 GB GPU
Limits
- No image input
- Behind 2026 models
Specifications
| Vendor | Meta AI |
|---|---|
| Category | LLM |
| Release | 2024-12 |
| Status | GA |
| License | Open weights |
| License name | Llama 3.3 Community License |
| Commercial use | Conditional |
| Parameters | 70B |
| Architecture | dense transformer |
| Context window | 131K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 40–48 GB |
| System RAM | 64–128 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | High |
| Vendor country | US |
| Vendor type | Frontier lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 40–48 GB. Approximate system RAM: 64–128 GB. API access is available.