---
base_model: Qwen/Qwen3-0.6B
tags: [gguf, llama.cpp, quantized, query-expansion, qmd]
---
# qmd-query-expansion-0.6B (GGUF)

GGUF conversion of the QMD Query Expansion model.

## Details
- **Base:** Qwen/Qwen3-0.6B
- **SFT:** tobil/qmd-query-expansion-0.6B-sft
- **GRPO:** none
- **Task:** Query expansion (lex/vec/hyde format)

## Prompt Format
```
<|im_start|>user
/no_think Expand this search query: your query here<|im_end|>
<|im_start|>assistant
```