DeepSeek-R1-Distill-1.5B Q4_K_M GGUF

This is a Q4_K_M quantized GGUF conversion of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B optimized for on-device inference with llama.cpp.

Model Details

Property Value
Original Model DeepSeek-R1-Distill-Qwen-1.5B
Parameters 1.5 billion
Quantization Q4_K_M (4-bit, medium quality)
File Size ~1.0 GB
Context Window 32,768 tokens
Architecture Qwen2 (distilled from DeepSeek-R1)

Intended Use

This model is optimized for:

  • Mobile/Edge Deployment: Runs efficiently on most iOS devices
  • llama.cpp Integration: Compatible with llama.cpp and its bindings
  • On-Device AI: Private, offline inference without cloud dependencies

Capabilities

  • Reasoning: Distilled from DeepSeek-R1 for enhanced reasoning
  • Step-by-step Thinking: Good at breaking down problems
  • Code Generation: Capable coding assistance
  • Mathematical Problem Solving: Strong analytical capabilities
  • Compact Size: Great quality-to-size ratio

Usage with llama.cpp

./llama-cli -m DeepSeek-R1-Distill-1.5B-Q4_K_M.gguf -p "Your prompt here" -n 512

License

This model is released under the MIT License.

Attribution

Downloads last month
9
GGUF
Model size
2B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jc-builds/DeepSeek-R1-Distill-1.5B-Q4_K_M-GGUF

Quantized
(234)
this model