Qwen2.5-Coder-32B-Instruct-Uncensored-Q8_0-GGUF
a quantized coding model
1 min readupdated
This is a Q8_0 GGUF conversion (a format built for running large language models efficiently on consumer hardware) of the uncensored Qwen2.5-Coder-32B language model. Built for writing code, debugging, and solving technical problems without strict censorship filters, it is ideal for developers who want a local coding assistant running directly on their own PC or server.
Key features
- Based on the uncensored version of Qwen2.5-Coder-32B
- High precision preserved via Q8_0 quantization
- Optimized to run via llama.cpp tools
- Supports both CLI and local server modes
What you can do
- Spin up a local server for code generation and autocomplete
- Use the command-line tool to quickly tackle programming tasks
- Plug the model into local IDEs and GGUF-compatible clients
Example
llama-cli --hf-repo ymarpro/Qwen2.5-Coder-32B-Instruct-Uncensored-Q8_0-GGUF --hf-file qwen2.5-coder-32b-instruct-uncensored-q8_0.gguf -p "The meaning to life and the universe is"Read more
DetailsFormat: GGUF (Q8_0 quantization)
Runtime tools: llama.cpp (CLI and Server)
Base model: thirdeyeai/Qwen2.5-Coder-32B-Instruct-Uncensored










Comments