LLM
Legacy
Open weights
Mixtral 8x7B
The reference model from the era when MoE went mainstream
Release2023-12-11
Context33K
Max output—
Parameters46.7B
Local / VRAM24–48 GB
LicenseOpen weights
Overview
Mixtral 8x7B is a model in the LLM category from Mistral AI. It was released in 2023-12-11. The vendor is based in France. Best for: The reference model from the era when MoE went mainstream.
Strengths
- Apache-2.0
- MoE efficiency
- Broad tooling
Limits
- 32K context
- Behind current models
Specifications
| Vendor | Mistral AI |
|---|---|
| Category | LLM |
| Release | 2023-12-11 |
| Status | Legacy |
| License | Open weights |
| License name | Apache-2.0 |
| Commercial use | Allowed |
| Parameters | 46.7B |
| Active parameters | 12.9B |
| Architecture | MoE transformer |
| Context window | 33K |
| Input modalities | Text |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 24–48 GB |
| System RAM | 32–64 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | High |
| Vendor country | France |
| Vendor type | Frontier lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 24–48 GB. Approximate system RAM: 32–64 GB. API access is available.