GraySoft
Model Comparison

teichai/gemma-4-31b-it-claude-opus-distill-ggufvsunsloth/deepseek-r1-distill-qwen-14b-gguf

Side-by-side comparison of teichai/gemma-4-31b-it-claude-opus-distill-gguf and unsloth/deepseek-r1-distill-qwen-14b-gguf: downloads, license, context length, tasks, and benchmarks.

teichai/gemma-4-31b-it-claude-opus-distill-gguf

TeichAI · —

> **Build Environment & Features:** > - **Fine-tuning Framework**: **Unsloth** > - **Reasoning Effort**: **High** > - This model bridges the gap between Google's exceptional open-weights architecture and Claude 4.6's profound reasoning capabilities, leveraging cutting-edge fine-…

unsloth/deepseek-r1-distill-qwen-14b-gguf

unsloth · —

We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-Alpaca.ipynb

Side-by-side Specifications

teichai/gemma-4-31b-it-claude-opus-distill-ggufunsloth/deepseek-r1-distill-qwen-14b-gguf
AuthorTeichAIunsloth
Pipeline Task
Librarytransformers
Downloads116,92290,574
Likes63104
LicenseUnknownUnknown
Context Length
Created2026-04-032025-01-20
Last Modified2026-04-152025-01-25
Tags
gguftext-generation-inferencellama.cppunslothgemma4reasoningdataset:TeichAI/Claude-Opus-4.6-Reasoning-887xdataset:TeichAI/Claude-Sonnet-4.6-Reasoning-1100xdataset:TeichAI/claude-4.5-opus-high-reasoning-250xdataset:Crownelius/Opus-4.6-Reasoning-2100x-formatted
transformersggufdeepseekqwenqwen2unslothenarxiv:2501.12948base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-14Bbase_model:quantized:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

View full details: teichai/gemma-4-31b-it-claude-opus-distill-gguf · unsloth/deepseek-r1-distill-qwen-14b-gguf