Mistral Models

View as Markdown

This page provides detailed technical specifications for the Mistral model family supported by NeMo Customizer. For information about supported features and capabilities, refer to Tested Models.

Mistral-7B-Instruct-v0.3

PropertyValue
CreatorMistral AI
Architecturetransformer
DescriptionMistral-7B-Instruct-v0.3 is an instruction-tuned model optimized for dialogue and instruction-following tasks.
Max I/O Tokens4096
Parameters7 billion
Training DataNot specified
Default Namemistralai/Mistral-7B-Instruct-v0.3
HuggingFacemistralai/Mistral-7B-Instruct-v0.3

Training Options

  • LoRA: 1x 80GB GPU, tensor parallel size 1
  • Full SFT: 1x 80GB GPU, tensor parallel size 1

Deployment Configuration

  • LoRA:
  • NIM Image: nvcr.io/nim/nvidia/llm-nim:1.15.5
  • GPU Count: 1x 80GB
  • Full SFT:
  • NIM Image: nvcr.io/nim/nvidia/llm-nim:1.15.5
  • GPU Count: 1x 80GB
  • Additional Environment Variables:
  • NIM_MODEL_PROFILE: vllm

Ministral-3-3B-Instruct-2512

PropertyValue
CreatorMistral AI
Architecturetransformer
DescriptionMinistral-3-3B-Instruct-2512 is a compact instruction-tuned model from Mistral AI designed for efficient deployment.
Max I/O Tokens4096
Parameters3 billion
Training DataNot specified
Default Namemistralai/Ministral-3-3B-Instruct-2512
HuggingFacemistralai/Ministral-3-3B-Instruct-2512

Training Options

  • LoRA: 1x 80GB GPU, tensor parallel size 1
  • Full SFT: 2x 80GB GPU, tensor parallel size 1

Deployment using NIM is not supported for this model.

Ministral-3-3B-Reasoning-2512

PropertyValue
CreatorMistral AI
Architecturetransformer
DescriptionMinistral-3-3B-Reasoning-2512 is a compact model from Mistral AI optimized for reasoning tasks.
Max I/O Tokens4096
Parameters3 billion
Training DataNot specified
Default Namemistralai/Ministral-3-3B-Reasoning-2512
HuggingFacemistralai/Ministral-3-3B-Reasoning-2512

Training Options

  • LoRA: 1x 80GB GPU, tensor parallel size 1
  • Full SFT: 2x 80GB GPU, tensor parallel size 1

Deployment using NIM is not supported for this model.