---
license: apache-2.0
tags:
- gemma
- gemma3
- tunix
- grpo
- reasoning
- thinking
- llama-cpp
- gguf-my-repo
library_name: transformers
base_model: chimbiwide/gemma-3-1b-it-thinking-32k-grpo-merged
---

# GemmaThink-32k-Q8_0-GGUF (GRPO Trained Model)

This model was trained using GRPO (Group Relative Policy Optimization) to generate structured reasoning traces.

## Training Details

- **Base Model**: google/gemma-3-1b-it
- **Training Method**: SFT + GRPO
- **LoRA Rank**: 32
- **LoRA Alpha**: 64.0
- **Framework**: Tunix (JAX)
- **Hardware**: v6e-1 TPU in Colab

## Output Format
```
<reasoning>step-by-step thinking process</reasoning>
<answer>final answer</answer>
```

## Quicklinks:

- ***[SFT Base Model](https://huggingface.co/chimbiwide/gemma-3-1b-it-thinking-32k-sft-base)***
- ***[SFT Base Model Q8 GGUF](https://huggingface.co/chimbiwide/gemma-3-1b-it-thinking-32k-sft-base-Q8_0-GGUF)***
- ***[GRPO Full Model](https://huggingface.co/chimbiwide/gemma-3-1b-it-thinking-32k-grpo-merged)***
- ***[Q8-GGUF](https://huggingface.co/chimbiwide/gemma-3-1b-it-thinking-32k-grpo-merged-Q8_0-GGUF)*** <-- You're here
- ***[Article](https://huggingface.co/blog/chimbiwide/gemma3think)***