---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- merge
- model-merging
- mergekit
- lazymergekit
- qwen3
- 4b
- text-generation
- causal-lm
- llama-cpp
- gguf-my-repo
datasets:
- Idavidrein/gpqa
metrics:
- accuracy
base_model: ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0
base_model_relation: merge
model-index:
- name: qwen3-4b-merged---configuration-1
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (Massive Multitask Language Understanding)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: accuracy
      value: 72.51
      name: MMLU (5-shot)
      verified: false
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (Graduate-level Physics Q&A)
      type: Idavidrein/gpqa
      config: gpqa_diamond
      split: test
      args:
        num_few_shot: 0
    metrics:
    - type: accuracy
      value: 45.45
      name: GPQA Diamond (0-shot)
      verified: false
---

# parrotrouter/Qwen3-4B-Instruct-2507-20250808-233922-0-Q8_0-GGUF
This model was converted to GGUF format from [`ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0`](https://huggingface.co/ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0-Q8_0-GGUF --hf-file qwen3-4b-instruct-2507-20250808-233922-0-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0-Q8_0-GGUF --hf-file qwen3-4b-instruct-2507-20250808-233922-0-q8_0.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0-Q8_0-GGUF --hf-file qwen3-4b-instruct-2507-20250808-233922-0-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo ParrotRouter/Qwen3-4B-Instruct-2507-20250808-233922-0-Q8_0-GGUF --hf-file qwen3-4b-instruct-2507-20250808-233922-0-q8_0.gguf -c 2048
```