---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- SmallThinker-3B-Preview
---
Quantizations of https://huggingface.co./PowerInfer/SmallThinker-3B-Preview

### Inference Clients/UIs
* [llama.cpp](https://github.com/ggerganov/llama.cpp)
* [KoboldCPP](https://github.com/LostRuins/koboldcpp)
* [ollama](https://github.com/ollama/ollama)
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [jan](https://github.com/janhq/jan)
* [GPT4All](https://github.com/nomic-ai/gpt4all)
---

# From original readme

We introduce **SmallThinker-3B-preview**, a new model fine-tuned from the [Qwen2.5-3b-Instruct](https://huggingface.co./Qwen/Qwen2.5-3B-Instruct) model. 

Now you can directly deploy SmallThinker On your phones with [PowerServe](https://github.com/powerserve-project/PowerServe).

## Benchmark Performance

| Model | AIME24 | AMC23 | GAOKAO2024_I | GAOKAO2024_II | MMLU_STEM | AMPS_Hard | math_comp |
|---------|--------|-------|--------------|---------------|-----------|-----------|-----------|
| Qwen2.5-3B-Instruct | 6.67 | 45 | 50 | 35.8 | 59.8 | - | - |
| SmallThinker | 16.667 | 57.5 | 64.2 | 57.1 | 68.2 | 70 | 46.8 |
| GPT-4o | 9.3 | - | - | - | 64.2 | 57 | 50 |

Limitation: Due to SmallThinker's current limitations in instruction following, for math_comp we adopt a more lenient evaluation method where only correct answers are required, without constraining responses to follow the specified AAAAA format.

Colab Link: [Colab](https://colab.research.google.com/drive/182q600at0sVw7uX0SXFp6bQI7pyjWXQ2?usp=sharing)
## Intended Use Cases

SmallThinker is designed for the following use cases:

1.  **Edge Deployment:** Its small size makes it ideal for deployment on resource-constrained devices.
2.  **Draft Model for QwQ-32B-Preview:** SmallThinker can serve as a fast and efficient draft model for the larger QwQ-32B-Preview model. From my test, in llama.cpp we can get 70% speedup (from 40 tokens/s to 70 tokens/s).