Model family
Mistral Models
Mistral models cover multilingual workflows, coding, MoE architectures, vision-language experiments, and efficient local or hosted deployments.
Best for
Chat
Use this family hub to compare Mistral variants for chat workflows, then open the detail page for deeper deployment notes.
Code
Use this family hub to compare Mistral variants for code workflows, then open the detail page for deeper deployment notes.
Vision
Use this family hub to compare Mistral variants for vision workflows, then open the detail page for deeper deployment notes.
MoE
Use this family hub to compare Mistral variants for moe workflows, then open the detail page for deeper deployment notes.
Variants
Mistral models grouped by workflow
Coding
Codestral 22B
Mistral AI · Mistral
Best for: Coding assistant workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Devstral
Mistral AI · Mistral
Best for: Developer and coding workflow evaluation
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Reasoning
Vision / multimodal
Pixtral Large
Mistral AI · Mistral
Best for: Vision-language assistant workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Pixtral 12B
Mistral AI · Mistral
Best for: Vision-language local and hosted experiments
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Local-friendly
Mistral Small 3.1
Mistral AI · Mistral
Best for: Builders who want a smaller capable model with permissive licensing and good local runtime support.
Local: A practical local candidate when quantized; still test memory use and context length on your hardware.
Mistral Large 2
Mistral AI · Mistral
Best for: Large multilingual assistant evaluation
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Mistral 8x22B Instruct
Mistral AI · Mistral
Best for: MoE assistant evaluation
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Mixtral 8x7B Instruct
Mistral AI · Mistral
Best for: MoE local and hosted baseline workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Mistral 7B Instruct
Mistral AI · Mistral
Best for: Local assistant baseline workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Ministral 8B
Mistral AI · Mistral
Best for: Efficient local workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Ministral 3B
Mistral AI · Mistral
Best for: Low-resource local workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Compare
All Mistral models in the directory
| Model | Type | Best for | Local runner notes | License | Detail |
|---|---|---|---|---|---|
| Mistral Small 3.1 | Chat | Builders who want a smaller capable model with permissive licensing and good local runtime support. | A practical local candidate when quantized; still test memory use and context length on your hardware. | Apache 2.0 | Open |
| Mistral Large 2 | Chat | Large multilingual assistant evaluation | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Pixtral Large | Vision | Vision-language assistant workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Pixtral 12B | Vision | Vision-language local and hosted experiments | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Codestral 22B | Code | Coding assistant workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Mistral 8x22B Instruct | Chat | MoE assistant evaluation | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Mixtral 8x7B Instruct | Chat | MoE local and hosted baseline workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Mistral 7B Instruct | Edge | Local assistant baseline workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Ministral 8B | Edge | Efficient local workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Ministral 3B | Edge | Low-resource local workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Mathstral 7B | Reasoning | Math and reasoning evaluation | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Devstral | Code | Developer and coding workflow evaluation | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |