Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
PowerInfer/SmallThinker-3B-Preview - GGUF
This repo contains GGUF format model files for PowerInfer/SmallThinker-3B-Preview.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4391.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
SmallThinker-3B-Preview-Q2_K.gguf | Q2_K | 1.377 GB | smallest, significant quality loss - not recommended for most purposes |
SmallThinker-3B-Preview-Q3_K_S.gguf | Q3_K_S | 1.588 GB | very small, high quality loss |
SmallThinker-3B-Preview-Q3_K_M.gguf | Q3_K_M | 1.724 GB | very small, high quality loss |
SmallThinker-3B-Preview-Q3_K_L.gguf | Q3_K_L | 1.841 GB | small, substantial quality loss |
SmallThinker-3B-Preview-Q4_0.gguf | Q4_0 | 1.998 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
SmallThinker-3B-Preview-Q4_K_S.gguf | Q4_K_S | 2.009 GB | small, greater quality loss |
SmallThinker-3B-Preview-Q4_K_M.gguf | Q4_K_M | 2.105 GB | medium, balanced quality - recommended |
SmallThinker-3B-Preview-Q5_0.gguf | Q5_0 | 2.384 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
SmallThinker-3B-Preview-Q5_K_S.gguf | Q5_K_S | 2.384 GB | large, low quality loss - recommended |
SmallThinker-3B-Preview-Q5_K_M.gguf | Q5_K_M | 2.439 GB | large, very low quality loss - recommended |
SmallThinker-3B-Preview-Q6_K.gguf | Q6_K | 2.793 GB | very large, extremely low quality loss |
SmallThinker-3B-Preview-Q8_0.gguf | Q8_0 | 3.616 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/SmallThinker-3B-Preview-GGUF --include "SmallThinker-3B-Preview-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf
), you can try:
huggingface-cli download tensorblock/SmallThinker-3B-Preview-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 223
Model tree for tensorblock/SmallThinker-3B-Preview-GGUF
Base model
Qwen/Qwen2.5-3B
Finetuned
Qwen/Qwen2.5-3B-Instruct
Finetuned
PowerInfer/SmallThinker-3B-Preview