neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16 - GGUF
This repo contains GGUF format model files for neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.
Our projects
| Forge | |
|---|---|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| Awesome MCP Servers | TensorBlock Studio |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜><think>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q2_K.gguf | Q2_K | 0.006 GB | smallest, significant quality loss - not recommended for most purposes |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q3_K_S.gguf | Q3_K_S | 0.006 GB | very small, high quality loss |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q3_K_M.gguf | Q3_K_M | 0.006 GB | very small, high quality loss |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q3_K_L.gguf | Q3_K_L | 0.006 GB | small, substantial quality loss |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q4_0.gguf | Q4_0 | 0.006 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q4_K_S.gguf | Q4_K_S | 0.006 GB | small, greater quality loss |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q4_K_M.gguf | Q4_K_M | 0.006 GB | medium, balanced quality - recommended |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q5_0.gguf | Q5_0 | 0.006 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q5_K_S.gguf | Q5_K_S | 0.006 GB | large, low quality loss - recommended |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q5_K_M.gguf | Q5_K_M | 0.006 GB | large, very low quality loss - recommended |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q6_K.gguf | Q6_K | 0.006 GB | very large, extremely low quality loss |
| DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-Q8_0.gguf | Q8_0 | 0.006 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/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-GGUF --include "DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-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/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'