LogoLogo
  • Welcome
  • News and updates
  • Subnet Status Update
  • Macromedia
  • Bittensor
    • DTAO
  • SUBNETS
    • Subnet 1 - Apex
      • Subnet 1: Getting Started
      • Subnet 1: Incentive Mechanism
      • Subnet 1: Base Miner Setup
      • Subnet 1: Roadmap
    • Subnet 9 - Pre-training
      • Subnet 9: Getting Started
      • Subnet 9: Incentive Mechanism
      • Subnet 9: Roadmap
    • Subnet 13 - Data Universe
      • Subnet 13: Getting Started
      • Subnet 13: Incentive Mechanism
      • Subnet 13: Roadmap
      • Subnet 13 API
    • Subnet 25 - Mainframe
      • Subnet 25: Getting Started
      • Subnet 25: Incentive Mechanism
      • Subnet 25: Roadmap
  • Subnet 37 - Finetuning
    • Subnet 37: Getting Started
    • Subnet 37: Miners
    • Subnet 37: Validators
    • Subnet 37: Incentive Mechanism
    • Subnet 37: Competitions
    • Subnet 37: Roadmap
  • CONSTELLATION - USER GUIDES
    • Apex
      • Navigating Apex
      • FAQs
    • Gravity
      • Scraping data
      • Managing and Collecting your data
      • FAQs
    • Nebula
      • Explore Nebula
      • Analyzing data
  • Developers
    • API Documentation
      • Introduction
      • SN1 - APEX
        • Endpoints
        • Agentic Tasks
        • Supported Models
        • Examples
      • SN13 - Gravity
        • Endpoints
        • Examples
    • Macrocosmos SDK
      • Installation
      • API Keys
      • APEX
      • Gravity
    • Tools
      • Macrocosmos MCP
Powered by GitBook
On this page
  1. Developers
  2. API Documentation
  3. SN1 - APEX

Supported Models

PreviousAgentic TasksNextExamples

Last updated 20 days ago

1. Meta-Llama 3.1 70B Instruct (Quantized)

"hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4"

Description: A quantized version of Meta AI's 70-billion-parameter model, optimized for multilingual dialogue applications.

Details:

  • Model Size: 70 billion parameters

  • Quantization: INT4 using AutoAWQ

  • Use Cases: Multilingual dialogue applications

More Information:

2. Mistral Small 3.1 24B Instruct

"mrfakename/mistral-small-3.1-24b-instruct-2503-hf"

Description: A 24-billion-parameter instruction-tuned model, focusing on text generation tasks.

Details:

  • Model Size: 24 billion parameters

  • Format: Hugging Face Transformers

  • Use Cases: Text generation tasks

More Information:

3. Gemma 3 27B (Upcoming)

Description: A 27-billion-parameter multimodal model from Google, capable of handling both text and image inputs.

Details:

  • Model Size: 27 billion parameters

  • Capabilities: Multimodal (text and image input, text output)

  • Use Cases: Question answering, summarization, reasoning

More Information:

To learn more about our Language Models please visit our

Meta-Llama 3.1 70B Instruct - Hugging Face
Mistral Small 3.1 24B Instruct - Hugging Face
Gemma 3 27B - Hugging Face
Substack