How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF:Q4_K_M
Quick Links

Qwen2.5-Coder-1.5B-Python (GGUF)

A fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct, specialized for generating clean, efficient, and well-structured Python code.

Model Details

  • Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
  • Fine-tuning Method: QLoRA (r=32, alpha=32) via Unsloth
  • Training Dataset: iamtarun/python_code_instructions_18k_alpaca (2,500 instruction-response pairs)
  • Quantization Format: Q4_K_M (GGUF)
  • Supported Languages: 29+ natural languages (inherited from Qwen2.5) and Python programming language
  • Chat Template: ChatML
Downloads last month
169
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. ๐Ÿ™‹ Ask for provider support

Model tree for Speaks38/Qwen2.5-Coder-1.5B-Python-GGUF

Quantized
(208)
this model