GGUF quantizations (multi-variant repo)
This repository bundles several GGUF exports of the same fine-tuned model, differing only by quantization method.
Lineage: quantized from user/merged.
Use with llama.cpp, Ollama, LM Studio, or other GGUF-capable runtimes. Pick a subfolder that matches your hardware.
Variants
| Folder | Quantization |
|---|---|
iq4_nl/ |
iq4_nl |
iq4_nl_gguf/ |
iq4_nl_gguf |
iq4_xs/ |
iq4_xs |
iq4_xs_gguf/ |
iq4_xs_gguf |
q4_k_m/ |
q4_k_m |
q4_k_m_gguf/ |
q4_k_m_gguf |