Mixtral 8x7B
by Mistral AI · open-source · Last verified 2026-03-17
Mistral AI's sparse mixture-of-experts model using 8 expert networks of 7B parameters each, activating only 2 per token. Matches GPT-3.5 performance while using a fraction of the compute at inference.
https://mistral.ai ↗B
B—Above Average
Adoption: AQuality: B+Freshness: C+Citations: AEngagement: F
Specifications
- License
- Apache 2.0
- Pricing
- open-source
- Capabilities
- text-generation, code-generation, reasoning, multilingual, efficient-inference
- Integrations
- huggingface, ollama, vllm, together-ai, aws-bedrock, groq
- Use Cases
- enterprise-deployment, chatbots, code-generation, translation, analysis
- API Available
- Yes
- Parameters
- 46.7B (12.9B active)
- Context Window
- 32K tokens
- Modalities
- text
- Training Cutoff
- Early 2024
- Tags
- llm, open-source, moe, efficient, sparse, mistral
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
69.4Adoption
82
Quality
78
Freshness
50
Citations
84
Engagement
0