---
license: apache-2.0
language:
- en
base_model:
- tikeape/Qwen-3-4B-Compilation-Experimental
---

# Qwen-3-4B-Compilation-Experimental GGUF

GGUF conversions and quantized builds of **Qwen-3-4B-Compilation-Experimental**, generated from `tikeape/Qwen-3-4B-Compilation-Experimental` using `llama.cpp`.

## Included files

| File | Quantization |
|---|---|
| `Qwen-3-4B-Compilation-Experimental-gguf-f16.gguf` | `f16` |
| `Qwen-3-4B-Compilation-Experimental-gguf-q4_0.gguf` | `q4_0` |

## Notes

- Filenames follow the pattern `base-gguf-<quant>.gguf`.
- Quantizations included: `f16`, `q4_0`.