TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kPublished:Dec 17, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill is a finetuned model developed by TeichAI, based on the nvidia/Nemotron-Cascade-14B-Thinking architecture. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for high-reasoning tasks, leveraging its foundation for complex problem-solving. The model is licensed under Apache-2.0.

Loading preview...

Model Overview

TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill is a finetuned language model developed by TeichAI. It is built upon the nvidia/Nemotron-Cascade-14B-Thinking base model, indicating a focus on advanced reasoning capabilities.

Key Characteristics

  • Developer: TeichAI
  • Base Model: Finetuned from nvidia/Nemotron-Cascade-14B-Thinking
  • Training Efficiency: Achieved 2x faster training speeds by utilizing Unsloth and Huggingface's TRL library.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

This model is likely optimized for applications requiring strong analytical and logical processing, given its "Thinking" and "High-Reasoning-Distill" nomenclature. Its efficient training process suggests a focus on practical deployment for complex tasks.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p