High Throughput Inference Recommendation: Mixtral 8x7B
High Throughput Inference → Mixtral 8x7B
Use Case Overview
Mixtral 8x7B by Mistral is a recommended option for the High Throughput Inference use case.
Recommended Models
| Rank | Vendor | Context Window | Score |
|---|
| #8 | Mistral | 32K | 35/100 |
| Benchmark | Score |
|---|
| MMLU | 77.2 |
| HUMANEVAL | 79.0 |
| GSM8K | 79.7 |
| MATH | 38.0 |
| BBH | 78.4 |
| GPQA | 43.0 |
Strengths
- Mixture-of-Experts architecture.
Requirements
- API key from mistral
- Input length within 32K context window