Hugging Peers

unity-coder-30b-GGUF

☆ Save
by wfwrigh
132 downloads 0 likes on Hugging Face updated

Model card

Unity Coder 30B - Q4_K_M + F16 GGUF

Quantized GGUF version of vishnuOI/unity-coder-30b for local inference.

  • Base model: vishnuOI/unity-coder-30b
  • Quantization: Q4_K_M + F16
  • Format: GGUF (llama.cpp)

Usage

Load directly in LM Studio, Ollama, or llama.cpp.

Full Disclaimer:

Needs testing and tweaks- as it stands, the q4_k_m version with base LM Studio settings performs worse than some newer models without Unity Lora training- consider it more of an experiment. If someone has better experience with the f16 or has a good configuration, let me know!