Views
No views yet
GGUF quantizations of a QLoRA fine-tune of [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it)
on a custom CNC lathe work-order dataset for 永詮機械 (Yong Chuan Machinery).
## Run with Ollama ollama run hf.co/Pauldyu57/gemma4-cnc-workorder-GGUF:Q4_K_MIf this repo is private, first add your Ollama SSH key to HuggingFace:1 cat ~/.ollama/id_ed25519.pub
2 # → paste into https://huggingface.co/settings/keys## Files
| Quant | Size | Notes |
|-----------|-----------|-----------------------------|
| F16 | ~7.5 GB | Reference |
| Q8_0 | ~4.3 GB | Near-lossless |
| Q5_K_M | ~3.0 GB | Good quality / size balance |
| Q4_K_M | ~2.5 GB | Default for CPU/small GPUs |