okjustgaming
/

loomy-nonthinking

8-bit precision

Model card Files Files and versions

Loomy Non-Thinking Model

A non-thinking model for EDW (Enterprise Data Warehouse) analytics tasks.

Model Details

Base Model: Mistral-Nemo-12B
Quantization: Q8_0 (8-bit)
Training: Fine-tuned for EDW analytics conversations
Version: v13e → nonthinking

Usage

Downloads last month: 156

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

Log In to add your hardware

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support