Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
unsloth/DeepScaleR-1.5B-Preview - GGUF
This repo contains GGUF format model files for unsloth/DeepScaleR-1.5B-Preview.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| DeepScaleR-1.5B-Preview-Q2_K.gguf | Q2_K | 0.753 GB | smallest, significant quality loss - not recommended for most purposes |
| DeepScaleR-1.5B-Preview-Q3_K_S.gguf | Q3_K_S | 0.861 GB | very small, high quality loss |
| DeepScaleR-1.5B-Preview-Q3_K_M.gguf | Q3_K_M | 0.924 GB | very small, high quality loss |
| DeepScaleR-1.5B-Preview-Q3_K_L.gguf | Q3_K_L | 0.980 GB | small, substantial quality loss |
| DeepScaleR-1.5B-Preview-Q4_0.gguf | Q4_0 | 1.066 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| DeepScaleR-1.5B-Preview-Q4_K_S.gguf | Q4_K_S | 1.072 GB | small, greater quality loss |
| DeepScaleR-1.5B-Preview-Q4_K_M.gguf | Q4_K_M | 1.117 GB | medium, balanced quality - recommended |
| DeepScaleR-1.5B-Preview-Q5_0.gguf | Q5_0 | 1.259 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| DeepScaleR-1.5B-Preview-Q5_K_S.gguf | Q5_K_S | 1.259 GB | large, low quality loss - recommended |
| DeepScaleR-1.5B-Preview-Q5_K_M.gguf | Q5_K_M | 1.285 GB | large, very low quality loss - recommended |
| DeepScaleR-1.5B-Preview-Q6_K.gguf | Q6_K | 1.464 GB | very large, extremely low quality loss |
| DeepScaleR-1.5B-Preview-Q8_0.gguf | Q8_0 | 1.895 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/DeepScaleR-1.5B-Preview-GGUF --include "DeepScaleR-1.5B-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/DeepScaleR-1.5B-Preview-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 605
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for tensorblock/DeepScaleR-1.5B-Preview-GGUF
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Finetuned
agentica-org/DeepScaleR-1.5B-Preview
Finetuned
unsloth/DeepScaleR-1.5B-Preview